Daily Papers

AI coding agents, software tools that automate development tasks through reasoning and tool use, are increasingly extended through plugin marketplaces, yet the structure, maintenance, and co-evolution dynamics of these emerging repositories remain empirically unexplored. Unlike traditional software packages that deliver functionality through source code, agent plugins deliver functionality through a combination of natural-language instruction files, scripts, and configuration files, raising the question of whether these plugins are maintained artifacts that co-evolve across components, or one-off artifacts that developers write once and do not need to revisit. To study the maintenance and co-evolution of agent plugins, we conduct an empirical study of 1,926 repositories hosting Claude Code plugin marketplaces, analyzing 8,351 plugins and 77,773 commits across 2,018 marketplaces. We find that the marketplace is expanding rapidly, plugin-touching commit activity growing 8.8x over six months after the October 2025 launch, and plugins targeting Software Engineering tasks accounting for 61.3% of all plugins. Plugin development is predominantly feature-driven, with feature commits occurring at more than twice the rate of conventional open-source software (OSS) (39.6% vs. 17.2%). Claude co-authors 34.9% of all commits, and four commit types (docs, perf, style, and refactor) carry substantially different meanings in plugin repositories than in traditional software. Most component types evolve independently, but within skills directories, natural-language instruction files and implementation scripts co-evolve at above-chance rates, with 78% of co-changes being functionally coupled, representing a new class of maintenance dependency not observed in traditional software engineering.

Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confabulate prior agreements. White-box approaches such as persona vectors require model weights and so cannot be applied to closed APIs (Claude, GPT-4) that most users actually interact with. We present Nautilus Compass, a black-box persona drift detector and agent memory layer for production coding agents. The method operates entirely at the prompt-text layer: cosine similarity between user prompts and behavioral anchor texts, aggregated by a weighted top-k mean using BGE-m3 embeddings. Compass is, to our knowledge, the only public agent memory layer (among Mem0, Letta, Cognee, Zep, MemOS, smrti verified May 2026) that does not call an LLM at index time to extract facts or build a graph; raw conversation text is embedded directly. The system ships as a Claude Code plugin, an MCP 2024-11-05 A2A server (Cursor, Cline, Hermes), a CLI, and a REST API on one daemon, with a Merkle-chained audit log for tamper-evident anchor updates. On a held-out test set built from real Claude Code session traces and labeled by an independent LLM judge, Compass reaches ROC AUC 0.83 for drift detection. The embedded retrieval pipeline scores 56.6% on LongMemEval-S v0.8 and 44.4% on EverMemBench-Dynamic (n=500), topping the four published EverMemBench Table 4 baselines. LongMemEval-S 56.6% is ~30 points below recent white-box leaders (90+%); we treat that as the architectural ceiling of the no-extraction design. End-to-end reproduction cost is $3.50 (~14x cheaper than GPT-4o-judged stacks). A paired cross-vendor behavior A/B accompanies these numbers as preliminary system-level evidence. Code, anchors, frozen test data, and audit-log tooling are MIT-licensed at github.com/chunxiaoxx/nautilus-compass.

Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its comprehensive architecture by analyzing the publicly available TypeScript source code and further comparing it with OpenClaw, an independent open-source AI agent system that answers many of the same design questions from a different deployment context. Our analysis identifies five human values, philosophies, and needs that motivate the architecture (human decision authority, safety and security, reliable execution, capability amplification, and contextual adaptability) and traces them through thirteen design principles to specific implementation choices. The core of the system is a simple while-loop that calls the model, runs tools, and repeats. Most of the code, however, lives in the systems around this loop: a permission system with seven modes and an ML-based classifier, a five-layer compaction pipeline for context management, four extensibility mechanisms (MCP, plugins, skills, and hooks), a subagent delegation mechanism with worktree isolation, and append-oriented session storage. A comparison with OpenClaw, a multi-channel personal assistant gateway, shows that the same recurring design questions produce different architectural answers when the deployment context changes: from per-action safety classification to perimeter-level access control, from a single CLI loop to an embedded runtime within a gateway control plane, and from context-window extensions to gateway-wide capability registration. We finally identify six open design directions for future agent systems, grounded in recent empirical, architectural, and policy literature.

The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language model and turns it into a coding agent able to act on a repository. The usage is loose and polysemous. Sometimes the term denotes the whole product (Claude Code, Codex CLI); sometimes it denotes the evaluation scaffold that runs an agent against tasks (the SWE-bench harness); sometimes it gets conflated with an agent framework, an SDK, an IDE plugin, or an orchestrator. What is missing is a reference definition that works as an instrument, one that includes and excludes cases consistently. We build that definition through a conceptual analysis that combines works with persistent identifiers and primary grey-literature sources, such as official documentation, glossaries, and engineering reports. We reconstruct the genealogy of the term, from the horse's tack to the classic test harness, to the machine-learning evaluation harness, and finally to the agent harness. We then propose a constitutive definition that states the necessary and sufficient conditions for a system to be an agent harness, we operationalize it as an inclusion and exclusion test, and we draw the boundary of the concept against an agent framework, an agent SDK, an IDE plugin, an eval harness, and an orchestrator. We apply the definition to six real harnesses (Claude Code, Codex CLI, Aider, Cline, OpenHands, and SWE-agent) and to deliberate edge cases; the test includes and excludes consistently. We close with a research agenda organized by design tension axes. The contribution is an operational definition of agent harness, with a shared vocabulary, able to guide engineering practice and the scientific comparison of agentic systems.

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing the web, the consequences of unsafe or adversarially manipulated behavior become immediate and tangible. Existing AI safety work has focused primarily on model alignment and input filtering, but these approaches do not address what happens at the moment an agent's intent becomes a real action on a real machine. This gap is especially acute in local environments, where developers run agents against their own filesystems, credentials, and infrastructure with little runtime control. This paper introduces AgentWall, a runtime safety and observability layer for local AI agents. AgentWall intercepts every proposed agent action before it reaches the host environment, evaluates it against an explicit declarative policy, requires human approval for sensitive operations, and records a complete execution trail for audit and replay. It is implemented as a policy-enforcing MCP proxy and native OpenClaw plugin, working across Claude Desktop, Cursor, Windsurf, Claude Code, and OpenClaw with a single install command. We present the design, architecture, threat model, and policy model of AgentWall, and demonstrate 92.9% policy enforcement accuracy with sub-millisecond overhead across 14 benchmark tests. AgentWall is open-source at https://github.com/agentwall/Agentwall.

Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the NL2Pipeline gap. To bridge it, we introduce DataFlow-Harness, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines DataFlow-Skills for procedural guidance, a Model Context Protocol (MCP) layer that exposes the live operator registry and current pipeline state, and DataFlow-WebUI, which synchronizes conversational authoring with a visual DAG editor. On a 12-task data-engineering benchmark, DataFlow-Harness achieves a 93.3\% observed end-to-end pass rate. Relative to Vanilla Claude Code, it reduces measured monetary cost by 72.5\% and generation latency by 49.9\%; its observed pass rate is within 0.9 percentage points of the Context-Aware Claude Code baseline while its cost is 42.8\% lower. Per-task analysis indicates that Skills are most useful when construction depends on implicit procedural knowledge. These results show that live platform grounding can produce persistent, editable workflow artifacts with an observed reliability close to script-generation baselines and with lower measured construction cost and latency.

Static analysis tools provide a powerful means to detect security vulnerabilities by specifying queries that encode vulnerable code patterns. However, writing such queries is challenging and requires diverse expertise in security and program analysis. To address this challenge, we present QLCoder - an agentic framework that automatically synthesizes queries in CodeQL, a powerful static analysis engine, directly from a given CVE metadata. QLCode embeds an LLM in a synthesis loop with execution feedback, while constraining its reasoning using a custom MCP interface that allows structured interaction with a Language Server Protocol (for syntax guidance) and a RAG database (for semantic retrieval of queries and documentation). This approach allows QLCoder to generate syntactically and semantically valid security queries. We evaluate QLCode on 176 existing CVEs across 111 Java projects. Building upon the Claude Code agent framework, QLCoder synthesizes correct queries that detect the CVE in the vulnerable but not in the patched versions for 53.4% of CVEs. In comparison, using only Claude Code synthesizes 10% correct queries.

LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering rank2026posttrainbench, novikov2025alphaevolve. We show that an autoresearch-style pipeline karpathy2026autoresearch powered by Claude Code discovers novel white-box adversarial attack algorithms that significantly outperform all existing (30+) methods in jailbreaking and prompt injection evaluations. Starting from existing attack implementations, such as GCG~zou2023universal, the agent iterates to produce new algorithms achieving up to 40\% attack success rate on CBRN queries against GPT-OSS-Safeguard-20B, compared to leq10\% for existing algorithms (fig:teaser, left). The discovered algorithms generalize: attacks optimized on surrogate models transfer directly to held-out models, achieving 100\% ASR against Meta-SecAlign-70B chen2025secalign versus 56\% for the best baseline (fig:teaser, middle). Extending the findings of~carlini2025autoadvexbench, our results are an early demonstration that incremental safety and security research can be automated using LLM agents. White-box adversarial red-teaming is particularly well-suited for this: existing methods provide strong starting points, and the optimization objective yields dense, quantitative feedback. We release all discovered attacks alongside baseline implementations and evaluation code at https://github.com/romovpa/claudini.

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key to this process are agent manifests, configuration files (such as Claude.md) that provide agents with essential project context, identity, and operational rules. However, the lack of comprehensive and accessible documentation for creating these manifests presents a significant challenge for developers. We analyzed 253 Claude.md files from 242 repositories to identify structural patterns and common content. Our findings show that manifests typically have shallow hierarchies with one main heading and several subsections, with content dominated by operational commands, technical implementation notes, and high-level architecture.

Using Large Language Models (LLMs) has gained popularity among software developers for generating source code. However, the use of LLM-generated code can introduce risks of adding suboptimal, defective, and vulnerable code. This makes it necessary to devise methods for the accurate detection of LLM-generated code. Toward this goal, we perform a case study of Claude 3 Haiku (or Claude 3 for brevity) on CodeSearchNet dataset. We divide our analyses into two parts: function-level and class-level. We extract 22 software metric features, such as Code Lines and Cyclomatic Complexity, for each level of granularity. We then analyze code snippets generated by Claude 3 and their human-authored counterparts using the extracted features to understand how unique the code generated by Claude 3 is. In the following step, we use the unique characteristics of Claude 3-generated code to build Machine Learning (ML) models and identify which features of the code snippets make them more detectable by ML models. Our results indicate that Claude 3 tends to generate longer functions, but shorter classes than humans, and this characteristic can be used to detect Claude 3-generated code with ML models with 82% and 66% accuracies for function-level and class-level snippets, respectively.

Human-written agent skills encode rich workflows for real-world problem solving, but are typically used as external inference-time instructions rather than internalized as reusable model capabilities. We introduce SkillGym, a framework that transforms these skills into executable, verifiable training environments for large language model agents. Its skill-to-task pipeline instantiates concrete tasks, verifies outcomes with code-based checkers, and assesses empirical skill dependence through contrastive executions. We construct and release 2,756 environments across 12 categories and collect 8,364 successful trajectories from multiple models and harnesses, averaging 49 tool calls and over 60k logged text tokens. These resources support supervised fine-tuning on verified workflows and reinforcement learning with outcome-based rewards. Under Claude Code, supervised fine-tuning improves Qwen3.5-35B-A3B by 199 Elo on GDPval-AA v2, 19.10 percentage points on Terminal-Bench 2.1, and 28.13 and 12.38 points on SkillsBench v1.1 with and without skills, respectively. Our 35B SkillGym-Agent reaches 51.47\% on skill-assisted SkillsBench, exceeding reported scores for Claude Sonnet 4.6, GPT-5.4 Mini, and DeepSeek V4 Pro. Without skills, it also surpasses skill-assisted bases under Codex and Claude Code, suggesting reusable procedural competence.

Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with higher execution costs. We introduce HarnessPro, a label-free method for evolving harnesses to improve task performance while reducing execution cost. In this setting, candidate harnesses are evaluated using LLM-generated tests without access to ground-truth solutions or official tests. Specialized agents diagnose execution trajectories, plan updates with different performance-cost priorities, and implement them as candidate harnesses. Rather than returning a single harness, HarnessPro uses normalized weighted squared-distance selection to provide cost-focused (lite), balanced (medium), and performance-focused (heavy) harnesses for different deployment budgets. Selected harnesses enter the next iteration, where execution feedback guides further updates. Our experiments cover Terminal-Bench 2, SWE-Bench Pro, and ProgramBench, using GPT-5.5 with Codex and GLM-5.2 with Claude Code. Across these benchmarks using GPT-5.5 with Codex, the heavy mode of HarnessPro achieves an average pass-rate gain of 2.0 percentage points and an average per-task cost reduction of 26.1% relative to RHO. This advantage also holds when using GLM-5.2 with Claude Code. Code is available at https://github.com/pzs19/HarnessPro

Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian -- written from scratch, not translated -- and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks. Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently substituting the model on 20% of tasks via an official safeguard fallback -- evidence that the deployed product, not the model, is the unit actually measured. Version 2 adds Round 2: seven further configurations on the same frozen set under a per-configuration freshness gate -- the Russian-market agents SourceCraft CLI (ds, legacy) and Koda CLI (koda-pro), Antigravity with Gemini 3.1 Pro and 3.5 Flash, and Codex CLI with GPT-5.6 Sol and Luna. SourceCraft's flagship resolves 68.1% (N=23), above GPT-5.5 and both Gemini rows. A tool-call contamination re-audit of all 437 Round-2 trajectories finds the Russian and Gemini columns clean (0/293 cells) while flagging systematic oracle-hunting in the GPT-5.6 family (8/69 and 13/75 cells), including one case of mining a prior round's artifacts from the run machine's disk; honest scores are published alongside raw ones. We release statements, metadata, trajectories, and diffs; oracles are withheld with a SHA-256 manifest.

Agentic code assistants are a new generation of AI systems capable of performing end-to-end software engineering tasks. While these systems promise unprecedented productivity gains, their behavior and effectiveness depend heavily on configuration files that define architectural constraints, coding practices, and tool usage policies. However, little is known about the structure and content of these configuration artifacts. This paper presents an empirical study of the configuration ecosystem of Claude Code, one of the most widely used agentic coding systems. We collected and analyzed 328 configuration files from public Claude Code projects to identify (i) the software engineering concerns and practices they specify and (ii) how these concerns co-occur within individual files. The results highlight the importance of defining a wide range of concerns and practices in agent configuration files, with particular emphasis on specifying the architecture the agent should follow.

Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, NotebookLM-based document synthesis for contextual understanding, and a Claude Code multi-agent system for code generation and validation. Our integrated approach leverages intent clarification, retrieval-augmented generation, and specialized sub-agents orchestrated via Claude's agent framework. We demonstrate that this method significantly improves the accuracy and reliability of code assistants in real-world repositories, yielding higher single-shot success rates and better adherence to project context than baseline single-agent approaches. Qualitative results on a large Next.js codebase show the multi-agent system effectively plans, edits, and tests complex features with minimal human intervention. We compare our system with recent frameworks like CodePlan, MASAI, and HyperAgent, highlighting how targeted context injection and agent role decomposition lead to state-of-the-art performance. Finally, we discuss the implications for deploying LLM-based coding assistants in production, along with lessons learned on context management and future research directions.

We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-quality datasets of executable 3D code, a coding harness for spatial reasoning and automated verification, and practical guidance for 3D coding. First, we construct 3DCodeVerse-2M, a large-scale curated dataset of standalone 3D executable code. We build this corpus by collecting open-source data, converting specialized representations, and generating new programs with coding agents. Each program is packaged with the source files and associated assets required for execution in its declared environment, along with available descriptions and verification records. Second, we develop the 3DCodeVerse Harness, a multi-agent directed acyclic graph framework for generating and refining 3D content. It uses execution checks, spatial measurements, and visual feedback to automatically evaluate and revise generated programs without human feedback during generation. Third, we conduct systematic empirical studies of 3D coding, establishing baselines with fine-tuned open models and deriving practical guidance through component-level analyses of our harness. Extensive experiments demonstrate that fine-tuning on our dataset significantly improves the 3D coding capabilities of open-source models. Notably, our 3DCodeVerse harness achieves a 90% win rate against Claude Design (3D Object) in pairwise human evaluations, when both are utilized by Claude Opus 5.5.

Current coding-agent benchmarks usually pro- vide the full task specification upfront. Real research coding often does not: the intended system is progressively disclosed through in- teraction, requiring the agent to track durable design commitments across a long session. We introduce a benchmark for this setting and study faithfulne Ss Loss U nder eM ergent s Pecification (SLUMP), defined as the reduc- tion in final implementation faithfulness un- der emergent specification relative to a single- shot specification control. The benchmark con- tains 20 recent ML papers (10 ICML 2025, 10 NeurIPS 2025), 371 atomic verifiable compo- nents, and interaction scripts of approximately 60 coding requests that progressively disclose the target design without revealing the paper itself. Final repositories are scored with a five-level component-faithfulness rubric and accompanied by an exposure audit to verify that scored components are recoverable from the visible interaction. Evaluated on Claude Code and Codex, the single-shot specification control achieves higher overall implementation fidelity on 16/20 and 14/20 papers, respectively. Structural integration degrades under emergent specification on both platforms, while seman- tic faithfulness loss is substantial on Claude Code and small on Codex. As a mitigation case study, we introduce ProjectGuard, an exter- nal project-state layer for specification tracking. On Claude Code, ProjectGuard recovers 90% of the faithfulness gap, increases fully faith- ful components from 118 to 181, and reduces severe failures from 72 to 49. These results identify specification tracking as a distinct eval- uation target for long-horizon coding agents.

We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.

Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs. Yet existing repository-level benchmarks typically evaluate only whether the final patch passes tests. Satisfying a user request requires a long chain of interdependent reasoning and decisions: an agent must recover explicit and implicit requirements, formulate a repository-grounded implementation plan, and translate it into correct code. A pass/fail outcome cannot characterize how an unsuccessful trajectory diverges from the requirements and implementation process needed for a correct patch. To address this gap, we introduce SWE-RPG, a repository-level benchmark that combines executable patch evaluation with validated ground-truth references (GTs) for (1) Requirement Clarification and (2) Implementation Planning. These intermediate GTs support retrospective, GT-aligned diagnosis of complete coding-agent trajectories across clarification, planning, code generation, and artifact submission. SWE-RPG comprises 163 tasks from 31 Python and Java repositories, including 113 bug fixes and 50 feature additions. We evaluate 3 coding agents, including Claude Code, Codex, and OpenCode, with 6 large language model backends, including Claude-Sonnet-5 and GPT-5.6-Terra. Results show that the evaluated popular coding agents still struggle to implement user requests in existing repositories, achieving an average resolved rate of only 31.5% on SWE-RPG. Intermediate-GT diagnosis further identifies implicit requirement recovery as the main bottleneck, accounting for 24.5%--46.0% of agent runs. This result suggests implicit-requirement recovery as a key candidate direction for improving coding agents. The benchmark data and evaluation code are available at https://github.com/Xin-Zhou-smu/SWE-RPG-Bench.

Generative AI coding agents are entering the open-source supply chain, yet their diverse and often invisible traces leave their prevalence poorly understood. We introduce a multi-layered detection framework that integrates configuration-file scanning, commit-message analysis, author-identity matching, and bot-signature lookup across World of Code (180M+ Git repositories), classifying agent traces into four behavioral types. No single method captures more than a fraction of activity: multi-method detection identifies 850,157 Claude Code commits in one snapshot, of which bot-account lookup_the signal most adoption studies rely on_recovers only 28,154 (3.3%), a 30x relative-recall gap, so single-signal prevalence estimates are biased low by at least this factor. Every detection pattern is hand-validated (495 labels) with per-cell precision and Wilson confidence intervals. Across snapshots from December 2024 to April 2026, commit-attributed agents generate over 320,000 commits per month; Claude Code leads (886,122 commits across 17,295 projects) and dominates silent, configuration-file-only adoption (21,078 projects). Compared against an independent pull-request census (AIDev), the two channels capture nearly disjoint agent populations_a PR census misses 79% of commit-detected Claude Code adopters and essentially all Codex adopters_and different kinds of work: PR-deployed cloud agents (Codex, Cursor) surface as feature work, while commit-deployed in-editor agents (Claude Code, OpenHands, Aider) surface as maintenance. The observed work profile follows deployment and detection mode rather than the tool itself, so no single channel is representative.

Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when the agent reads matching files. We call these files the agent's harness. Developers add to it whenever they correct the agent, but one success proves little: the same agent can pass a task once and fail it the next time. We present Cortex, a tool that tests changes to the harness instead of trusting them. It saves fixes from the developer's sessions as replayable tasks, finds the corrections that recur, writes one skill or rule at a time, and keeps it only if repeated runs with and without it show a net gain and no task made noticeably worse. Existing text is tested the same way before it is deleted, and Cortex neither adds nor deletes text the agent never used. We tested Cortex with Claude Haiku 4.5 on a repository built for the purpose, with conventions the model tends to break, one area with nothing to learn, and a script playing the developer. On held-out tasks, the harnesses it built made the agent follow the conventions far more often than no skills or rules did, left the comparison area unchanged, and added no text read on every turn. Rules, which load automatically, did most of the work; skills helped only when offered with the files a task touches, and those offered on every turn were rarely opened. Cortex kept none of the useless or harmful suggestions we planted, but the agent never opened the useless ones or the harmful skills, and it reached no verdict on the harmful rules, so the test shows that Cortex keeps no unused text, not that it detects damage. Under the stronger Claude Sonnet 5 a single run's harness added little, and on a real open-source project, where the agent was rarely corrected, Cortex found nothing to learn. We release the tool, the lab and its data.

In CLAUDE.md, "do not" is a natural-language instruction that the model interprets. Claude Code's deny is a built-in control that blocks an action before the agent can take it. Both can express the same security goal, but they control the agent in different ways. We measure this gap in 481 public CLAUDE.md files. An LLM matched the extracted candidate rules against Claude Code's documented controls, and two security practitioners independently checked a sample without seeing the model's answers or each other's labels. Depending on how closely a control had to match the written rule, only about 4-16% of the retrieved security rules had a matching built-in control. Under the strictest standard the estimate was 4.4% (95% CI: 2.6-6.7%), and the two annotators agreed closely on which rules had a match. A manual review of complete files found that our extraction method captured 66.3% of eligible security rules; the reported rates therefore apply to the rules it captured. This is a usable security problem: CLAUDE.md is a write-only channel. A developer writes a security rule but gets no feedback on whether a control will enforce it. The same plain-text form hides two kinds of rule: those a permission rule, mode, or sandbox can enforce, and those left to the model to interpret.

Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper documents a failure mode in Claude Code where partial standard output from timed-out commands (exit code 143) is recorded in compaction summaries as confirmed results, propagating false positives across sessions and model versions without re-verification. The underlying mechanism is a conflation of observation and persistence, where information that appeared in the terminal is treated as equivalent to information written to durable storage. This finding extends the analysis of LLM self-evaluation failures reported in prior work on non-determinism in LLM-as-judge grading by showing that agentic tools exhibit analogous reliability deficits when reporting on their own operational outcomes. The failure has direct implications for any workflow that relies on agentic session continuity for data processing, scientific computation, or multi-step automation.

Large language models (LLMs) are increasingly being integrated into software development processes. The ability to generate code and submit pull requests with minimal human intervention, through the use of autonomous AI agents, is poised to become a standard practice. However, little is known about the practical usefulness of these pull requests and the extent to which their contributions are accepted in real-world projects. In this paper, we empirically study 567 GitHub pull requests (PRs) generated using Claude Code, an agentic coding tool, across 157 diverse open-source projects. Our analysis reveals that developers tend to rely on agents for tasks such as refactoring, documentation, and testing. The results indicate that 83.8% of these agent-assisted PRs are eventually accepted and merged by project maintainers, with 54.9% of the merged PRs are integrated without further modification. The remaining 45.1% require additional changes benefit from human revisions, especially for bug fixes, documentation, and adherence to project-specific standards. These findings suggest that while agent-assisted PRs are largely acceptable, they still benefit from human oversight and refinement.

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. This creates a distinct safety challenge in that harmful behavior may emerge through sequences of individually plausible steps, including intermediate actions that appear locally acceptable but collectively lead to unauthorized actions. We present AgentHazard, a benchmark for evaluating harmful behavior in computer-use agents. AgentHazard contains 2,653 instances spanning diverse risk categories and attack strategies. Each instance pairs a harmful objective with a sequence of operational steps that are locally legitimate but jointly induce unsafe behavior. The benchmark evaluates whether agents can recognize and interrupt harm arising from accumulated context, repeated tool use, intermediate actions, and dependencies across steps. We evaluate AgentHazard on Claude Code, OpenClaw, and IFlow using mostly open or openly deployable models from the Qwen3, Kimi, GLM, and DeepSeek families. Our experimental results indicate that current systems remain highly vulnerable. In particular, when powered by Qwen3-Coder, Claude Code exhibits an attack success rate of 73.63\%, suggesting that model alignment alone does not reliably guarantee the safety of autonomous agents.

Autoformalization translates informal mathematical theorems into code for proof assistants such as Lean. A central challenge is that current evaluation metrics can accept type-correct but misaligned statements or reject correct statements written in a different formulation. Inspired by Pass@k, we propose SA-Pass (*Semantic Alignment Pass*), which tests formal statements using auxiliary statements called *shadows* that characterize the intended statement. A generated statement receives full credit only when it compiles, implies each shadow (forward check), and is implied by their conjunction (backward check). We instantiate SA-Pass in ShadowBench, a Lean 4 full autoformalization benchmark of 178 postgraduate- to research-level problems spanning eight mathematical areas. Claude Code (Opus 4.8) with Numina-Lean-Agent reaches 61.8% compile rate and 11.2% SA-Pass. Across outputs generated by six agentic configurations, SA-Pass achieves 98.8% binary agreement with expert judgments. An early version of ShadowBench served as the benchmark for Track 4 of the ICML 2026 AI4Math Challenge.

Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verification. Despite rapid progress, research-level proofs often depend on concepts missing from leading proof assistant libraries (e.g., Lean's Mathlib), and successful compilation does not guarantee that a translation preserves the theorem's meaning or the proof's reasoning. Furthermore, aligned NL-FL training data are scarce, and leading agents often rely on costly frontier models and manually engineered harnesses. To address the above issues, we present AIProver, an agentic framework for autonomous proof auto-formalization and proof synthesis (AFPS) that jointly post-trains a 119B open-weight language model and evolves its agentic, tool-calling harness with HarnessEvolve. Verifiers assess type correctness, proof completeness, and semantic correctness, returning rewards and diagnostic certificates that drive model fine-tuning and alternating reinforcement learning via symbolic feedback and HarnessEvolve, a certificate-driven evolutionary search over the whole harness control flow that re-tailors the harness to the updated model. For research-level training and evaluation, we introduce LoCoBench, 58.9k instances from Mathlib, CSLib, Mizar Math Library, and a bounded-arithmetic textbook, with a 771-instance validation split whose theorem-proof pairs have no public Lean formalization. Against 39 frameworks spanning AFPS agents, frontier LLMs, and coding agents, AIProver lifts pass@4 semantic correctness over its Leanstral-1.5 base from 15.7% to 36.7% and outperforms every other open-weight system and Aristotle. As a Claude Code and Codex skill, it lifts their semantic correctness from 41.9% and 34.1% to 79.8% and 62.4%, respectively. Further, it is also 24% cheaper than Numina-Lean-Agent, pushing the accuracy-cost frontier of research-level AFPS.

Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving framework on CLEVER, a Lean 4 benchmark for verifiable code generation. Our results show that Claude generates arguably valid specifications for 98.8% of problems (with 81.3% also accepted by CLEVER's isomorphism-based scoring on the correct portion of the benchmark), certifies implementations against correct ground-truth specifications for 87.5% of problems, and reaches a 98.1% success rate on the end-to-end program generation and verification pipeline over entries with self-consistent premises. Across all stages, Claude further provides high-quality feedback on its own attempts (as confirmed under manual review), identifying underlying causes of failure and lingering bugs in the dataset. These findings highlight a growing mismatch between the difficulty of existing program verification benchmarks and the capabilities of modern agentic provers, and point to the need for more rigorous, bug-resilient evaluation methodologies, and in particular for alternatives to isomorphism-based scoring of generated specifications. More broadly, our results provide empirical evidence that tight compiler-in-the-loop agentic paradigms are currently the most effective approach for foundational program verification.

Context-reduction layers for API-based coding agents, including command-output compressors, retrieval rankers, and API-boundary proxies, are commonly evaluated by how much context or tool output they remove. We ask a different question: which interventions actually reduce end-to-end billed cost while preserving task success? Our primary evidence is a pre-specified, hash-frozen, paired campaign of 2,908 provider-billed Claude Code runs, of which 2,848 were analyzed, covering 103 tasks, seven repositories, and three models. The campaign compared a baseline with two generations of hook-based compression and an API-boundary proxy within a broader measured program of roughly 5,500 billed executions. Three findings emerge. First, prompt-cache traffic dominated cost composition, accounting for about 87% of reconstructed four-component cost (about 80% of the actual bill), with an 8.7% dollar-weighted residual not attributable from retained telemetry. Second, local payload reduction was not a reliable predictor of end-to-end billed cost. An arm that removed 38% of estimated raw tool-output tokens incurred 6.8% higher paired cost (95% CI: +2.8% to +11.3%), while per-task reduction showed only a weak association with cost change (Pearson r = 0.15). Third, aggressive compression can remove action-critical evidence: on SWE-bench-derived Go tasks, compression reduced successful patch application from 27/40 to 15/40 by corrupting verbatim edit anchors. We propose evaluating context-reduction systems by success-adjusted billed cost rather than token reduction alone.

The recently released model, Claude 3.5 Computer Use, stands out as the first frontier AI model to offer computer use in public beta as a graphical user interface (GUI) agent. As an early beta, its capability in the real-world complex environment remains unknown. In this case study to explore Claude 3.5 Computer Use, we curate and organize a collection of carefully designed tasks spanning a variety of domains and software. Observations from these cases demonstrate Claude 3.5 Computer Use's unprecedented ability in end-to-end language to desktop actions. Along with this study, we provide an out-of-the-box agent framework for deploying API-based GUI automation models with easy implementation. Our case studies aim to showcase a groundwork of capabilities and limitations of Claude 3.5 Computer Use with detailed analyses and bring to the fore questions about planning, action, and critic, which must be considered for future improvement. We hope this preliminary exploration will inspire future research into the GUI agent community. All the test cases in the paper can be tried through the project: https://github.com/showlab/computer_use_ootb.

Like any other discipline, Large Language Models (LLMs) have significantly impacted software engineering by helping developers generate the required artifacts across various phases of software development. This paper presents a case study comparing the performance of popular LLMs GPT, Claude, Gemini, and DeepSeek in generating functional specifications that include use cases, business rules, and collaborative workflows for a web application, the Mess Management System. The study evaluated the quality of LLM generated use cases, business rules, and collaborative workflows in terms of their syntactic and semantic correctness, consistency, non ambiguity, and completeness compared to the reference specifications against the zero-shot prompted problem statement. Our results suggested that all four LLMs can specify syntactically and semantically correct, mostly non-ambiguous artifacts. Still, they may be inconsistent at times and may differ significantly in the completeness of the generated specification. Claude and Gemini generated all the reference use cases, with Claude achieving the most complete but somewhat redundant use case specifications. Similar results were obtained for specifying workflows. However, all four LLMs struggled to generate relevant Business Rules, with DeepSeek generating the most reference rules but with less completeness. Overall, Claude generated more complete specification artifacts, while Gemini was more precise in the specifications it generated.

Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branches the effective history, so the learning object is a tree rather than a sequence. Existing linearizations either retain the rightmost path, causing time-travel leakage, or replay a depth-first traversal, causing train-inference mismatch. We introduce two exact, gradient-equivalent corrections: LogitTree, a segmented K-forward traversal, and a packed 4D attention mask. LogitTree requires K+1 backward passes; the 4D mask requires a custom kernel and white-box eviction records. We also propose SDCC (Self-Distillation for Conditioning Consistency), a single-backward-pass variational relaxation. At each eviction, it minimizes forward KL between the compressed student and a stop-gradient teacher on the reconstructed pre-eviction prefix. A residual per-junction KL of epsilon_KL gives an O(sqrt(epsilon_KL)) bound on the train-deployment total-variation gap. SDCC also applies to black-box harnesses. On seven web-search benchmarks with TC-RAG, AgentFold, MemexRL, Claude Code, and OpenCode, naive training inflates the train-rollout log-probability gap, especially on eviction-heavy batches. The exact methods stay at the no-compression floor, and SDCC substantially closes the gap, with lower logit drift and higher rollout rewards.

Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. Existing benchmarks do not faithfully evaluate LLMs in real-world bug hunting scenarios because they rely on fuzzing harnesses, target-specific descriptions, or vulnerability-reproduction tasks. We present SEC-bench Pro, a benchmark for measuring agent bug hunting on critical, high-complexity software systems. This work discloses reports with concrete PoC inputs and links fixes into reproducible tasks through a three-phase pipeline for vulnerability collection, environment reconstruction, and oracle-based validation. We instantiate SEC-bench Pro with 183 validated vulnerabilities across V8 and SpiderMonkey, including a V8 subset with more than $1.5 million in cumulative Google Vulnerability Reward Program awards. These instances span memory-safety, sandbox, JIT, and race-condition bugs under browser-grade and runtime-grade execution conditions. Our evaluation shows that coding agents with frontier models remain below 40% success on both evaluated engines. The open-weight Kimi-K2.6 baseline reaches 11.7% on V8, while the strongest frontier configuration reaches 32.0% on V8 and 38.8% on SpiderMonkey. ClaudeCode and Codex solve complementary instance sets, and their two-agent union reaches 37.9% on V8 and 48.8% on SpiderMonkey. SEC-bench Pro provides robust environments for assessing LLM-based security agents and exposes limitations in long-horizon bug hunting tasks.

Since language models (LMs) now outperform average humans on many challenging tasks, it has become increasingly difficult to develop challenging, high-quality, and realistic evaluations. We address this issue by examining LMs' capabilities to generate code for solving real scientific research problems. Incorporating input from scientists and AI researchers in 16 diverse natural science sub-fields, including mathematics, physics, chemistry, biology, and materials science, we created a scientist-curated coding benchmark, SciCode. The problems in SciCode naturally factorize into multiple subproblems, each involving knowledge recall, reasoning, and code synthesis. In total, SciCode contains 338 subproblems decomposed from 80 challenging main problems. It offers optional descriptions specifying useful scientific background information and scientist-annotated gold-standard solutions and test cases for evaluation. Claude3.5-Sonnet, the best-performing model among those tested, can solve only 4.6% of the problems in the most realistic setting. We believe that SciCode demonstrates both contemporary LMs' progress towards becoming helpful scientific assistants and sheds light on the development and evaluation of scientific AI in the future.

Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters. We run the missing crossed comparison: an integrity-clean three-arm ablation (baseline / bash_only / code_only) on synthetic computation tasks and SWE-bench Mini modification tasks, holding model, harness, and prompts fixed, with two agents (Claude Code, OpenAI Codex CLI) so the comparison spans both regime and agent-design axes. Across the four resulting (regime, agent) cells, restricting the agent to a single execute_code MCP tool is cheaper than -- or statistically tied with -- its cheapest tool-rich rival in three cells (significantly on Artifact/Claude and SWE-bench/Codex; directionally on Artifact/Codex), with pass rates statistically tied within each cell. The lone exception is SWE-bench/Claude, where code_only is directionally costlier (+14.4%, not significant); a conditional-cost analysis localizes that gap to failure-cost on doomed-run trajectories, not a per-edit tax on successful runs. Two implications: the cheapest tool surface is jointly determined by task regime and agent design rather than by either axis alone, and the headline cost signal lives in cache-adjusted cost -- not pass rate, which is invariant across surfaces at the model sizes we evaluate. The benchmark harness, task suite, and analysis code are available at https://github.com/hyang0129/onlycodes.

Persistent context files (AGENTS.md, CLAUDE.md) are standard practice for guiding AI coding agents, yet evidence for their effectiveness is contradictory. We present a controlled ablation of context-injection strategy across two frontier agents (Claude Code and Codex), 17 real tasks from 3 repositories (15 shared + 2 Codex-only), and 288 evaluated runs with gold-test evaluation. Context strategy does not measurably move correctness on either agent (bounded to <=10-15pp via equivalence testing). A failure-mode triage reveals why: agents fail on implementation skill---feature design, pattern selection, exact wiring---not missing repository knowledge that a context file could supply; a manipulation probe confirms the real AGENTS.md never converts a near-miss to a pass on either agent. We further show that borderline task difficulty is agent-specific (Spearman rho=0.75), offering a candidate explanation for prior contradictions: single-agent studies draw tasks from different agents' informative bands. We release all code, data, and analysis.

Open-source libraries and tools are widely reused, but compatibility maintenance is expensive. Once maintainers leave, useful repositories can stop working as runtimes and dependencies evolve. We study whether LLM agents can adapt old repositories to modern environments, a task we call compatibility rescue. Unlike bug repair, compatibility rescue starts from a repository that worked in its original environment but fails after ecosystem drift. RepoRescue gives agents only the repository and its failing modern environment; the agent must diagnose the failure, locate affected code, and produce a source-code rescue that restores the historical test suite. We build RepoRescue from 193 Python and 122 Java repositories, each verified to pass historically and fail after modernization. We evaluate five deployed agent systems on Python and three on Java. Beyond full-patch pass rate, we rerun patches after removing test-file edits to measure source-only repair, add a runtime-enforced regime that blocks test edits, and validate practical use for repositories whose suites pass after rescue. We find that Claude Code systems sometimes edit failing tests even when prompted not to; with runtime blocking, Kimi still rescues 41.5% of repositories. Systems are complementary: their union reaches 62.7%, exceeding the best single system by 10.9 points. Difficulty concentrates in cross-file coordination: on 14 repositories requiring coordinated whole-codebase changes, GPT-5.2 through Codex passes all 14, while every Claude Code system passes at most two. Finally, a passing suite is only an initial signal: among 34 unmaintained Python candidates whose suites pass after rescue, 22 work in realistic scenarios and 12 pass bug-hunt with patches that address the compatibility failure. RepoRescue benchmarks compatibility rescue with source-only auditing, runtime enforcement, practical validation, and reasoning labels.

Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and output-grain choices that change cohorts and downstream conclusions. We introduce M4Bench, 28 clinical derivation tasks across 15 task families on MIMIC-IV and eICU, to test whether AI coding agents can reproduce such derivations and how clinician-reviewed agent skills change their results. Its controls decompose the value of skills into specification completeness, delivery format, and schema familiarity. In a Docker-isolated Codex campaign (GPT 5.4 Mini and GPT 5.5), skills raise reward by 0.136 over the no-skill baseline, with 26 of 28 tasks improving. Specification completeness accounts for most of this gain: on an eight-task control subset, an operational spec alone raises reward by 0.162, and skills add only 0.024 on top, indistinguishable from zero. On a ten-task subset, decoy skills score like no skill and raw reference SQL nearly matches targeted skills, arguing against generic context or the skill format as the explanation. Schema obfuscation and restructuring preserve 86% and 70% of the skill gain (GPT 5.4 Mini, 26 MIMIC-IV tasks), a descriptive robustness check rather than a bound on memorization. A descriptive Claude Code replication on all 28 tasks (Opus 4.7 and Sonnet 4.6, 560 runs) is directionally consistent (+0.120, 21 of 28 tasks improving). These gains are partial agreement with the reference, not completed tasks: only 25 of 280 with-skill and 13 of 280 no-skill Codex runs pass every strict check, and skills barely change which rows agents return (key F1 +0.003). Skills are released as a versioned, clinician-reviewable markdown delivery format, with a family-level reference-validity audit. M4Bench releases tasks, skills, evaluation code, and sanitized per-run evidence as an open-source benchmark.

Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely capture continuous maintenance at the granularity of package releases, where changes are bundled, shipped, and inherited by subsequent versions. We present SWE-Chain, a benchmark for evaluating agents on chained release-level package upgrades, where each transition builds on the agent's prior codebase. To produce upgrade specifications, we design a divide-and-conquer synthesis pipeline that aligns release notes with code diffs for each version transition, ensuring the requirements are grounded in actual code changes, informative to agents, and feasible to implement. SWE-Chain contains 12 upgrade chains across 9 real Python packages, with 155 version transitions and 1,660 grounded upgrade requirements. Across nine frontier agent-model configurations, agents achieve an average of 44.8% resolving, 65.4% precision, and 50.2% F1 under the Build+Fix regime, with Claude-Opus-4.7 (Claude Code) leading at 60.8% resolving, 80.6% precision, and 68.5% F1. These results show that SWE-Chain is both feasible and discriminative, and reveal that current agents still struggle to make correct upgrades across chained package releases without breaking existing functionality.

Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the existing mature software stack that engineers have developed over decades to access sensors and control motion. Yet prior work primarily engineers complex custom harnesses to orchestrate agents for robot use, particularly by prescribing specialized workflows and providing bespoke interfaces. This raises the question: "Is such additional harness engineering necessary?" We introduce OpenRUA, a zero-abstraction harness that bypasses bespoke abstraction layers by providing off-the-shelf coding agents with only terminal access to the robot's native software interface ROS 2. OpenRUA employs a minimalist workspace-as-harness design, only offering ROS 2 documentation and basic tools while leaving the coding agent to organize its own work without orchestrating any agentic workflow. Within this workspace, OpenRUA recasts perception as file I/O and manipulation as coding. With Claude Code powered by Claude Opus 5, OpenRUA achieves success rates of 99.0% on CaP-Bench and 87.0% on LIBERO-PRO, demonstrating that an off-the-shelf coding agent can serve as a zero-shot visuomotor policy through the robot's native interface, without bespoke primitives or task-specific training. Under this minimalist design, further analysis reveals striking emergent behaviors of coding agents: (1) For perception, the agent spontaneously writes programs that process raw sensory inputs and derive metric measurements in 96.80% of episodes. (2) For manipulation, the agent spontaneously builds motion-control clients (e.g., gripper control) in 95.87% of episodes and closed-loop control programs (e.g., adjusting motion based on sensor feedback) in 50.13% of episodes. Our code is available at https://github.com/terminalworld/OpenRUA.

Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, whereas real-world developers use them to continuously build, update, and maintain large-scale projects. This mismatch motivates us to evaluate agents over sequences of realistic coding tasks, where we find that agents exhibit recurring environment-dependent token costs that existing methods struggle to reduce. To minimize these costs, we introduce TokenEconomizer, an external controller that cuts environment-specific token costs over a sequence of tasks. These cuts come from determining (i) which operational micro-skills to inject, (ii) which persistently irrelevant tools to prune, and (iii) when to intervene in unproductive failure loops. Across Claude Code, Codex, and GitHub Copilot CLI paired with frontier models, TokenEconomizer reduces the average token cost by 18.4-30.9% with comparable task success. Savings hold in every repository under every tested agent-model setting and generalize to diverse domains such as sequential web development and security auditing, where costs fall by 6.4-21.2% depending on task structure. Our work establishes adaptive black-box cost control as a promising direction for reducing token costs of coding agents in realistic settings.

Evaluating the real-world applicability of large language models (LLMs) provides valuable insights for their development and use in software development tasks. Existing benchmarks often focus on standalone coding problems or specific libraries, overlooking multi-file, project-based scenarios and lacking a rigorous evaluation of consistency. The HackerRank-ASTRA Benchmark introduces project-based coding problems that mirror real-world scenarios. It evaluates model consistency through 32 runs (k = 32) and median standard deviation while incorporating taxonomy-level analysis to assess sub-skill capabilities. Initial evaluations on 65 problems show that the top three models -- o1, o1-preview, and Claude-3.5-Sonnet-1022 -- achieved comparable average scores of 75%, with no statistically significant differences in performance. Notably, Claude-3.5-Sonnet-1022 demonstrated the highest consistency across problems, with low variability (SD = 0.0497), which was statistically significant compared to other models, highlighting its reliability for real-world software development tasks.

Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing benchmarks often center on localized tasks or end-state outcomes, offering limited insight into sustained execution. We introduce LOOPSBENCH, a long-horizon benchmark for loop engineering in coding agent evaluation. Each task is a dependency DAG over separately testable development units with source-evidenced prerequisite edges. LOOPSBENCH comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains. Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations. We evaluate frontier coding agents paired with widely used loop implementations. The strongest configuration, Opus-4.7 with Claude Code and outer continuation, resolves 25.00% of tasks. Recorded plans recover only part of the source-recovered prerequisite DAG, and regression events remain visible across the evaluated loop profiles. We open source the benchmark data and code, including all tasks, more than 5,300 development units, and executable tests, at microsoft/Loopsbench.

Large language models excel at function- and file-level code generation, yet generating complete repositories from scratch remains a fundamental challenge. This process demands coherent and reliable planning across proposal- and implementation-level stages, while natural language, due to its ambiguity and verbosity, is ill-suited for faithfully representing complex software structures. To address this, we introduce the Repository Planning Graph (RPG), a persistent representation that unifies proposal- and implementation-level planning by encoding capabilities, file structures, data flows, and functions in one graph. RPG replaces ambiguous natural language with an explicit blueprint, enabling long-horizon planning and scalable repository generation. Building on RPG, we develop ZeroRepo, a graph-driven framework for repository generation from scratch. It operates in three stages: proposal-level planning and implementation-level refinement to construct the graph, followed by graph-guided code generation with test validation. To evaluate this setting, we construct RepoCraft, a benchmark of six real-world projects with 1,052 tasks. On RepoCraft, ZeroRepo produces repositories averaging nearly 36K LOC, roughly 3.9times the strongest baseline (Claude Code) and about 64times other baselines. It attains 81.5% functional coverage and a 69.7% pass rate, exceeding Claude Code by 27.3 and 35.8 percentage points, respectively. Further analysis shows that RPG models complex dependencies, enables progressively more sophisticated planning through near-linear scaling, and enhances LLM understanding of repositories, thereby accelerating agent localization.

Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored. Existing benchmarks often prioritize functional correctness, overlooking the nuanced requirements found in real-world development. We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions: constraint type, hierarchical levels, and iterative refinement. Built upon a structured taxonomy of 9 categories and 27 constraint types, MultiCodeIF enables granular assessment of both functional and non-functional instruction adherence. Using an automated pipeline, ConstraGen, we synthesize and evolve 2,021 code tasks sourced from 14 programming languages, supporting multi-turn evaluation through feedback-driven task variants. Empirical evaluation of six state-of-the-art LLMs uncovers substantial performance disparities. The top-performing model, Claude-3-7-Sonnet, achieves 63.0% average constraint satisfaction, while smaller models like Qwen3-1.7B fall to 44.8%. Models perform well on explicit constraints, but struggle with implicit or abstract constraints. Tasks with multiple hierarchical constraints significantly reduce model success rates, from 54.5% in single-level to just 18.8% in multi-level scenarios. However, structured feedback enables progressive improvement: average constraint satisfaction rises from 63.0% to 83.4% over four iterative refinement rounds. MultiCodeIF provides a scalable, constraint-aware, and feedback-sensitive framework to benchmark LLMs under realistic code generation scenarios, bridging the gap between synthetic evaluations and real-world instruction complexity. The full benchmark dataset, evaluation pipeline, and source code are available at https://github.com/SYSUSELab/MultiCodeIF.

Coding agents can modify and test code across large software projects. Game development is a domain where agents must implement gameplay rules. A game can end in a valid state even after violating its rules during the run. Current game-development benchmarks replay fixed examples, score videos, or ask another model to judge the result. However, no existing benchmark checks game rules throughout execution across varied evaluator-selected scenarios while ensuring exactly reproducible verdicts. We introduce GameLogicBench, a benchmark of 72 gameplay-logic tasks in Godot projects. An automated evaluator checks each game's rules at every simulation tick. Across 403 hand-designed scenarios, seeded parameter variations produce 1,451 test cases. To ensure that the evaluator measures behavior rather than implementation choice, it must accept different correct implementations for each task while rejecting mutants, implementations with one required capability removed. The tasks span isolated mechanics, multi-system interactions, and repository-scale features. Across 20 combinations of language models and scaffolds, the best observed run solves 52.78% of tasks. Under Claude Code, all twelve models solve fewer tasks as task scope expands from isolated mechanics, through interacting systems, to repository-scale features. Agents inspect code more often and make more tool calls on repository-scale tasks than on isolated-mechanic tasks. Most unsuccessful submissions are runnable, but implement some required game behavior incorrectly. We compared versions of our benchmark evaluator built with and without validation using mutants. Without this validation, incorrect agent submissions passed. A separate analysis finds agents copying code from public repositories when network access is open. Reliable evaluation thus depends both on what the tests reject and on what external code agents can access.

Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons.

Refactoring is a common software engineering practice that improves code quality without altering program behavior. Although tools like ReExtractor+, RefactoringMiner, and RefDiff have been developed to detect refactorings automatically, they rely on complex rule definitions and static analysis, making them difficult to extend and generalize to other programming languages. In this paper, we investigate the viability of using foundation models for refactoring detection, implemented in a tool named RefModel. We evaluate Phi4-14B, and Claude 3.5 Sonnet on a dataset of 858 single-operation transformations applied to artificially generated Java programs, covering widely-used refactoring types. We also extend our evaluation by including Gemini 2.5 Pro and o4-mini-high, assessing their performance on 44 real-world refactorings extracted from four open-source projects. These models are compared against RefactoringMiner, RefDiff, and ReExtractor+. RefModel is competitive with, and in some cases outperform, traditional tools. In real-world settings, Claude 3.5 Sonnet and Gemini 2.5 Pro jointly identified 97% of all refactorings, surpassing the best-performing static-analysis-based tools. The models showed encouraging generalization to Python and Golang. They provide natural language explanations and require only a single sentence to define each refactoring type.

Real-world frontend development requires agents to compose reproduction, generation, modification, and repair over an evolving application state. Learning a general policy for this process requires translating heterogeneous execution feedback into task-aligned rewards and effective credit assignment across long sequences of interdependent actions. We introduce WebCoder, a general frontend development agent trained with artifact-grounded agentic reinforcement learning. Our key idea is to assess diverse development activities through their effects on a shared executable artifact and its satisfaction of task requirements. We build Webdev-World, an executable environment that integrates code editing, application execution, browser inspection, and on-demand skills while preserving project state across interactions. An independent verifier evaluates the final application against task requirements to provide terminal rewards, while changes in intermediate artifact progress redistribute the resulting rollout advantage across development segments. Context compaction and message-tree sample construction support training on trajectories beyond a single context window while avoiding repeated loss computation on shared generated history. We further introduce Webdev-Bench to evaluate composed development requirements within a single project. On Webdev-Bench, WebCoder-27B raises requirement satisfaction from 64.8 for its Qwen3.8-27B base model to 72.8, exceeding Claude-Opus-4.8 (65.1) and GPT-5.4 (59.6); on Vision2Web, it improves the average visual and functional score from 41.1 to 62.4, on par with Claude-Opus-4.8. Ablation studies confirm the contributions of artifact-grounded credit assignment and long-horizon training.

AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark, a comprehensive evaluation of secure code generation by coding agents. Built from 150 real vulnerabilities, its 450 tasks span seven widely used languages (Java, C, C++, JavaScript, Python, PHP, and Go), 24 CWEs including 21 of the 2025 CWE Top 25 and 8 of the Top 10 KEV weaknesses, more than any benchmark we compare with, and three vibe-coding scenarios: filling in a function, writing a file, and building a repository's source tree from scratch. Every task asks only for functionality, through a specification that never mentions security, and hidden functional and security tests grade the result. Across six frontier agents, 73.6% to 91.3% of tasks pass functionally, yet even the strongest, Claude Fable 5, produces code that is both functional and secure for only 25.1% of tasks, and the others for 16.4% to 24.7%. The best model only passes 12% of the vulnerability scenarios across all vibe coding setting, posing strong concern on the security of the code written by vibe coding.

Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain specialization methods for LLMs to learn and utilize domain knowledge and data. However, existing domain-specific code benchmarks cannot evaluate the effectiveness of domain specialization methods, which focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge, lacking explicit knowledge corpora for developing domain specialization methods. To this end, we present KOCO-BENCH, a novel benchmark designed for evaluating domain specialization methods in real-world software development. KOCO-BENCH contains 6 emerging domains with 11 software frameworks and 25 projects, featuring curated knowledge corpora alongside multi-granularity evaluation tasks including domain code generation (from function-level to project-level with rigorous test suites) and domain knowledge understanding (via multiple-choice Q&A). Unlike previous benchmarks that only provide test sets for direct evaluation, KOCO-BENCH requires acquiring and applying diverse domain knowledge (APIs, rules, constraints, etc.) from knowledge corpora to solve evaluation tasks. Our evaluations reveal that KOCO-BENCH poses significant challenges to state-of-the-art LLMs. Even with domain specialization methods (e.g., SFT, RAG, kNN-LM) applied, improvements remain marginal. Best-performing coding agent, Claude Code, achieves only 34.2%, highlighting the urgent need for more effective domain specialization methods. We release KOCO-BENCH, evaluation code, and baselines to advance further research at https://github.com/jiangxxxue/KOCO-bench.

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers. This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and completing test cases under specific conditions. Spanning from simple assertion completions to writing test cases that cover specific code blocks across multiple files, these tasks are based on 12 python repositories, analyzing 845 problems with context lengths ranging from 4k to 128k tokens. Utilizing code testing frameworks, we propose a method to construct retrieval contexts using coverage information. While models exhibit comparable performance with short contexts, notable differences emerge with 16k contexts. Notably, models like GPT-4o and Claude 3.5 can effectively leverage relevant snippets; however, all models score below 35\% on the complex Task III, even with the oracle context provided, underscoring the benchmark's significance and the potential for model improvement. The benchmark is containerized for code execution across tasks, and we will release the code, data, and construction methodologies.

AI coding agents are reshaping software development through both autonomous and human-mediated pull requests (PRs). When developers use AI agents to generate code under their own accounts, code authorship attribution becomes critical for repository governance, research validity, and understanding modern development practices. We present the first study on fingerprinting AI coding agents, analyzing 33,580 PRs from five major agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, Claude Code) to identify behavioral signatures. With 41 features spanning commit messages, PR structure, and code characteristics, we achieve 97.2% F1-score in multi-class agent identification. We uncover distinct fingerprints: Codex shows unique multiline commit patterns (67.5% feature importance), and Claude Code exhibits distinctive code structure (27.2% importance of conditional statements). These signatures reveal that AI coding tools produce detectable behavioral patterns, suggesting potential for identifying AI contributions in software repositories.

Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats. While synthetic data has proven transformative for language models, code remains largely unexplored beyond limited quality improvements. We present CodeAlchemy, a synthetic data generation framework that transforms publicly sourced code into semantically-rich training data through 5 strategies: CodeEnhance (quality-aware rewriting), CodeQA (template-based problems), CodeDev (developer tasks), CodeDialogue (multi-turn conversations), and CodeTrace (execution traces). We process 3 corpora across 15 languages to generate 500B+ tokens of synthetic data plus 350B reasoning tokens, orders of magnitude more than prior efforts. CodeTrace instruments and executes 1.3M+ files across 14 languages and 5K libraries, capturing control flow, state tracking, and library knowledge. We introduce DevEval (developer tasks) and TraceEval (execution prediction) benchmarks; frontier models like Claude Sonnet 4.5 achieve only 5.6% exact match on TraceEval, revealing critical gaps in semantic understanding. Our 3B models achieve 83.5% on HumanEval, 63.2% on MBPP, 8.09% win rate on DevEval, and 15.36 ROUGE-2 on TraceEval, outperforming frontier models 10x the size including 27B Gemma-3 and 32B Granite-4.0.

Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities. We consider real-world software engineering to be a rich, sustainable, and challenging testbed for evaluating the next generation of language models. We therefore introduce SWE-bench, an evaluation framework including 2,294 software engineering problems drawn from real GitHub issues and corresponding pull requests across 12 popular Python repositories. Given a codebase along with a description of an issue to be resolved, a language model is tasked with editing the codebase to address the issue. Resolving issues in SWE-bench frequently requires understanding and coordinating changes across multiple functions, classes, and even files simultaneously, calling for models to interact with execution environments, process extremely long contexts and perform complex reasoning that goes far beyond traditional code generation. Our evaluations show that both state-of-the-art proprietary models and our fine-tuned model SWE-Llama can resolve only the simplest issues. Claude 2 and GPT-4 solve a mere 4.8% and 1.7% of instances respectively, even when provided with an oracle retriever. Advances on SWE-bench represent steps towards LMs that are more practical, intelligent, and autonomous.

Coding agents such as Claude Code and Codex close the software loop: a main agent manages the loop, subagents analyze and execute, tools do the work. We port this architecture to robot-policy improvement, where one difference dominates the design: robotic tools---trained policies, training pipelines, data collection---fail routinely, so a tool's quality must be measured, recorded at every call, and expired when the artifact behind it changes. AgenticRobotics is a backend-independent control plane in which an LLM controller drives disposable workers through durable train--evaluate--improve transactions: an immutable objective, controller-owned measurement, commit-keyed crash recovery, an evidence-graded skill library, and a tool registry with a standardized, recorded call surface. The title is an operational claim, not a selection claim: the operator can leave because promotion is evidence-gated, state is recoverable, and capability quality is derived from records---not because the loop picks better checkpoints than a human; on the one lineage we measured, it does not. The gates measurably buy false-promotion control (0.001 per run hardened versus 0.005--0.021 shipped), anytime-valid decisions under optional stopping, zero lost or duplicate effects under kill injection, and six of six artifact-tampering classes caught by a signed verifier.

Vision-language models (VLMs) have shown strong capabilities in generating visualization code from textual or visual specifications. However, real-world visualization authoring is inherently iterative: users frequently revise existing visualizations to repair flawed charts or adapt them to desired styles. Existing benchmarks primarily evaluate generation from scratch, leaving visualization code editing from multimodal feedback largely unexplored. We introduce VisEditBench, a benchmark of 1,395 human-annotated visualization code-editing tasks grounded in realistic visualization workflows and failure cases. VisEditBench covers two practical settings: feedback-guided repair, where models revise visualization code using buggy or marked charts together with textual feedback, and reference-guided restyling, where models modify code to match a target chart image. Evaluating 20 state-of-the-art VLMs reveals that visualization code editing remains challenging: Claude-4.6-Sonnet achieves the best overall pass rate of 74.46%, while most open-source models remain below 50%. Performance is particularly weak on visually grounded style adaptation, where Claude-4.6-Sonnet achieves only 55.71%. To establish a strong baseline, we further propose VisEditAgent, a render-grounded editing framework that iteratively generates, executes, validates, and refines candidate edits. Built on GPT-4o, VisEditAgent improves overall pass rate from 55.75% to 67.99%, demonstrating the importance of render-grounded feedback for faithful visualization editing. We will release VisEditBench at https://github.com/vis-nlp/VisEditBench.

We propose Step-by-Step Coding (SBSC): a multi-turn math reasoning framework that enables Large Language Models (LLMs) to generate sequence of programs for solving Olympiad level math problems. At each step/turn, by leveraging the code execution outputs and programs of previous steps, the model generates the next sub-task and the corresponding program to solve it. This way, SBSC, sequentially navigates to reach the final answer. SBSC allows more granular, flexible and precise approach to problem-solving compared to existing methods. Extensive experiments highlight the effectiveness of SBSC in tackling competition and Olympiad-level math problems. For Claude-3.5-Sonnet, we observe SBSC (greedy decoding) surpasses existing state-of-the-art (SOTA) program generation based reasoning strategies by absolute 10.7% on AMC12, 8% on AIME and 12.6% on MathOdyssey. Given SBSC is multi-turn in nature, we also benchmark SBSC's greedy decoding against self-consistency decoding results of existing SOTA math reasoning strategies and observe performance gain by absolute 6.2% on AMC, 6.7% on AIME and 7.4% on MathOdyssey.

A coding agent is a language model wrapped in a harness: the system prompt, the tool set, and the context management that turn a chat model into something that can work inside a repository. Production harnesses ship releases daily, vendors advertise pass-rate gains from harness changes, and leaderboards mix harnesses freely. What is rarely measured is how much the harness itself moves the score when the model is held fixed. We run five models through three production harnesses, Claude Code, mini-SWE-agent, and OpenCode, on SWE-bench Verified, and rerun the same configurations to calibrate how much a score moves when nothing changes but the run. On 447 tasks and the two models we ran there, Claude Code and mini-SWE-agent, the heaviest and the lightest harness, are equivalent within five points. On a 45-task hard subset and five models, swapping the harness flips as many tasks as rerunning the same harness, 13% in both cases, and the tasks a harness wins in one run are not the tasks it wins in the next. The one harness effect that clears the noise is a loss, not a gain: OpenCode trails by up to 9 points on the large pool, and on one model half of that gap sits in runs its output cap cut short. What the harness does decide is the bill. With the same model, the same tasks, and one price list, cost per task differs by up to 3x across harnesses. The gap is set at the first call, by the preamble of system prompt and tool schemas each harness sends with every step, and scaled by the number of steps; per-step growth and per-call tool output differ far less. The provider's price for cached input scales the bill and does not reorder it. The rerun data also give the resolution a harness comparison needs: at the discordance we observe, 45 tasks catch a 13-point gap only half the time and no gap with 80% power, and 447 tasks resolve 5 points, still coarser than the gains many harness changes claim.

Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little supervision. Although it is increasingly adopted, are vibe coding outputs really safe to deploy in production? To answer this question, we propose SU S VI B E S, a benchmark consisting of 200 feature-request software engineering tasks from real-world open-source projects, which, when given to human programmers, led to vulnerable implementations. We evaluate multiple widely used coding agents with frontier models on this benchmark. Disturbingly, all agents perform poorly in terms of software security. Although 61% of the solutions from SWE-Agent with Claude 4 Sonnet are functionally correct, only 10.5% are secure. Further experiments demonstrate that preliminary security strategies, such as augmenting the feature request with vulnerability hints, cannot mitigate these security issues. Our findings raise serious concerns about the widespread adoption of vibe-coding, particularly in security-sensitive applications.

While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question unaddressed: What constitutes a minimal viable pipeline for skill optimization, where every component is justified by theory or empirical necessity? We formalize skill optimization via Zeroth-Order (ZO) optimization, mapping classical counterparts (central difference, trust regions) to recent literature. Noting that unlike blind numerical perturbations in classical ZO, skill trajectories serve as interpretable debugging feedback. Grounded in Claude Code philosophy and PAC learning, we establish three principles for convergence and generalization: file-system-based trajectory exploration, consensus attribute mining, and independent validation gating. Eliminating redundancies, we propose SkillOpt-Lite. It accelerates convergence and outperforms full SkillOpt: improving LiveMath by +8.8 points on GPT-5.5 and +25.4 points on GPT-5.4-nano, allowing the nano model to surpass standard GPT-5.4 optimized by SkillOpt. Finally, we integrate our framework into production coding agents like VSCode Copilot, enabling developers to evolve agent skills via one line of vibe. Because our framework treats all agent components simply as standard editable code, this minimal pipeline naturally generalizes to full harness optimization (HarnessOpt). On SpreadsheetBench, HarnessOpt enables GPT-5.4-nano to achieve 0.7758 accuracy, outperforming the larger GPT-5.5 running standard pipelines (0.7620). Code is available at https://github.com/EvolvingLMMs-Lab/SkillOpt-Lite.

With the rapid advancement of powerful large language models (LLMs) in recent years, a wide range of software engineering tasks can now be addressed using LLMs, significantly enhancing productivity and scalability. Numerous benchmark datasets have been developed to evaluate the coding capabilities of these models, while they primarily focus on problem-solving and issue-resolution tasks. In contrast, we introduce a new coding benchmark MIGRATION-BENCH with a distinct focus: code migration. MIGRATION-BENCH aims to serve as a comprehensive benchmark for migration from Java 8 to the latest long-term support (LTS) versions (Java 17, 21), MIGRATION-BENCH includes a full dataset and its subset selected with 5,102 and 300 repositories respectively. Selected is a representative subset curated for complexity and difficulty, offering a versatile resource to support research in the field of code migration. Additionally, we provide a comprehensive evaluation framework to facilitate rigorous and standardized assessment of LLMs on this challenging task. We further propose SD-Feedback and demonstrate that LLMs can effectively tackle repository-level code migration to Java 17. For the selected subset with Claude-3.5-Sonnet-v2, SD-Feedback achieves 62.33% and 27.00% success rate (pass@1) for minimal and maximal migration respectively. The benchmark dataset and source code are available at: https://huggingface.co/collections/AmazonScience and https://github.com/amazon-science/self_debug respectively.

LLM-based agents struggle to execute complex, multi-step Standard Operating Procedures (SOPs) that are fundamental to industrial automation. Existing benchmarks fail to capture the procedural complexity and tool orchestration demands of real-world workflows. We introduce SOP-Bench, a benchmark of 2,000+ tasks from human expert-authored SOPs across 12 business domains (healthcare, logistics, finance, content moderation, etc.). Using a human-AI collaborative framework, experts crafted authentic SOPs while AI generated artifacts (tools, APIs, datasets), all human-validated, yielding realistic tasks with executable interfaces and ground-truth outputs. SOP-Bench serves as a research enabler for systematically investigating agent architectures, model capabilities, and deployment considerations across diverse procedural tasks. We demonstrate its utility through illustrative experiments with a subset of frontier models across Function-Calling (FC) and ReAct agents, revealing critical insights. For example, (1) newer models do not guarantee better performance - Claude 4 family outperforms Claude 4.5 family on ReAct tasks (Claude 4 Opus: 72.4% vs. Claude 4.5 Sonnet: 63.3% task success rate), demonstrating that production upgrades require validation; (2) no single model-agent combination dominates: best performances range from 57% to 100% depending on domain. These examples illustrate how SOP-Bench enables isolating and studying specific dimensions of agent performance without costly production experiments. Our goal is not to rank model capabilities or build optimal agents, but to provide a rigorous evaluation framework that enables the researchers and practitioners to systematically investigate agent design choices, model selection, and deployment strategies. We release the benchmark at https://github.com/amazon-science/sop-bench.

Code agents spend much of their effort simply locating the right code inside a repository. Two approaches dominate current practice. In Semantic Search, the agent retrieves code blocks from a vector index built from the repository in advance. In Deep Agentic Search (also known as grep-search by subagent), a planning agent delegates the exploration to a separate subagent that works in an isolated context window and returns only a condensed result. The second design, which is considered good context engineering practice, exists to protect the main agent from context pollution (also known as context rot), the loss of accuracy that occurs as unrelated material accumulates in the context window. Recent code agents (such as Claude Code, Codex, Antigravity, etc) have adopted it quickly, but there is little evidence on whether it produces better answers. We compare the two approaches on SWE-QA, a benchmark for repository-level code question answering. Semantic search answered 65.2% of questions correctly against 46.2% for deep agentic search, and it produced each correct answer at less than half the cost. To explain the gap, we then coded every failed run into a taxonomy of failure modes. The taxonomy shows that deep agentic search did not remove failures but introduced a new class of them: the single largest share of its failures, 41.8%, occurred at the hand-off between the planner and its sub-agent, and these were usually silent, ending in a fluent and confident answer that was wrong. Deep agentic search addresses a real problem and is now the preferred design in many code agents. However, our results show that the protection it offers may not be free, and that for read-only questions over a repository that can be indexed, retrieval was the stronger and cheaper option.

Agentic coding -- software development workflows in which autonomous coding agents plan, implement, and submit code changes with minimal human involvement -- is rapidly gaining traction. Prior work has shown that Pull Requests (PRs) produced using coding agents (Agentic-PRs) are accepted less often than PRs that are not labeled as agentic (Human-PRs). The rejection reasons for a single agent (Claude Code) have been explored, but a comparison of how rejection reasons differ between Agentic-PRs generated by different agents has not yet been performed. This comparison is important since different coding agents are often used for different purposes, which can lead to agent-specific failure patterns. In this paper, we inspect 654 rejected PRs from the AIDev dataset covering five coding agents, as well as a human baseline. Our results show that seven rejection modes occur only in Agentic-PRs, including distrust of AI-generated code. We also observe agent-specific patterns (e.g., automated withdrawal of inactive PRs by Devin), reflecting differences in how agents are configured and used in practice. Notably, a large proportion of rejected PRs (67.9%) lack explicit reviewer feedback, making their rejection reasons difficult to determine. To mitigate this issue, we propose a set of heuristics that reduce the proportion of such cases, offering a practical preprocessing step for future studies of PR rejection in agentic coding.

Code Agents have achieved remarkable advances in recent years, exhibiting strong capabilities across a wide range of software engineering tasks. However, their misuse often produces bloated and disorganized code that impairing readability, extensibility, and robustness. Despite this risk, existing benchmarks largely evaluate functional correctness rather than long-term maintainability of code agents. In this paper, we propose SmellBench, an extensible code refactoring benchmark that proactively injects code smells into clean code snippets from real-world repositories. This design enables the generation of controlled, high-quality, and diverse refactoring cases with human-written ground truth. Specifically, it contains 294 cases spanning 7 popular smell types, 3 difficulty levels, 2 instruction settings across 7 real-world repositories. We further design 3 evaluation aspects covering functional correctness, localization ability, and refactoring quality assessment. Experiments with 2 popular agents and 6 large langauge models (LLMs) show that the best combination - Qwen Code + Claude Sonnet 4.5 - achieved only a 50.34 score of smell elimination. Further analysis reveals that this gap arises from a focus on local code smells and a lack of cross-file understanding, which hinders comprehensive smell elimination.

Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and user-interaction feedback, current code agents rely only on simple code execution for feedback and verification. This approach fails to capture the actual quality of the generated code. In this paper, we propose WebGen-Agent, a novel website-generation agent that leverages comprehensive and multi-level visual feedback to iteratively generate and refine the website codebase. Detailed and expressive text descriptions and suggestions regarding the screenshots and GUI-agent testing of the websites are generated by a visual language model (VLM), together with scores that quantify their quality. The screenshot and GUI-agent scores are further integrated with a backtracking and select-best mechanism, enhancing the performance of the agent. Utilizing the accurate visual scores inherent in the WebGen-Agent workflow, we further introduce Step-GRPO with Screenshot and GUI-agent Feedback to improve the ability of LLMs to act as the reasoning engine of WebGen-Agent. By using the screenshot and GUI-agent scores at each step as the reward in Step-GRPO, we provide a dense and reliable process supervision signal, which effectively improves the model's website-generation ability. On the WebGen-Bench dataset, WebGen-Agent increases the accuracy of Claude-3.5-Sonnet from 26.4% to 51.9% and its appearance score from 3.0 to 3.9, outperforming the previous state-of-the-art agent system. Additionally, our Step-GRPO training approach increases the accuracy of Qwen2.5-Coder-7B-Instruct from 38.9% to 45.4% and raises the appearance score from 3.4 to 3.7.

AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scripts, and tool permissions. Because a skill is at once code and agent-facing instruction, it introduces a supply chain dependency whose risk is neither pure code nor pure prompt. Detection tools have never been measured against verified ground truth spanning this hybrid space, leaving their effectiveness unknown and wild-only evaluations biased. We present MalSkillBench, the first runtime-verified benchmark of malicious agent skills: 3,944 malicious skills labeled along a three-dimensional taxonomy of 108 cells. Of these, 3,214 come from a closed-loop Generate-Verify-Feedback pipeline admitting only samples whose malicious behavior fires inside a Docker sandbox under system-call monitoring and an LLM judge; we add 703 in-the-wild and 4,000 matched benign skills. Our measurements are consistent: code injection reaches 94.5% verification yield but prompt injection only 75.8%, the same fragility that later makes it hard to detect; the wild sample is narrow, dominated by one cryptocurrency-theft campaign (86.6% one behavior, 81% from two accounts) with a small but architecturally new tail attacking the agent control plane; the strongest skill-specific detector reaches 98.4% recall on code injection yet collapses on prompt-injection and agent-control attacks, and wild-only scoring swings the ranking by up to 66 recall points; supply-chain scanners and prompt-injection defenses each see only half of a skill, and no combination recovers the code-instruction relationship. Detecting malicious skills therefore requires reasoning jointly over task intent, code, and instructions. We release the dataset, pipeline, baselines, and results.

Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models such as Codex, CodeGen, and PanGu-Coder. To evaluate the effectiveness of these models, multiple existing benchmarks are proposed, including only cases of generating a standalone function, i.e., a function that may invoke or access only built-in functions and standard libraries. However, non-standalone functions, which typically are not included in the existing benchmarks, constitute more than 70% of the functions in popular open-source projects, and evaluating models' effectiveness on standalone functions cannot reflect these models' effectiveness on pragmatic code generation scenarios. To help bridge the preceding gap, in this paper, we propose a benchmark named CoderEval, consisting of 230 Python and 230 Java code generation tasks carefully curated from popular real-world open-source projects and a self-contained execution platform to automatically assess the functional correctness of generated code. CoderEval supports code generation tasks from six levels of context dependency, where context refers to code elements such as types, APIs, variables, and consts defined outside the function under generation but within the dependent third-party libraries, current class, file, or project. CoderEval can be used to evaluate the effectiveness of models in generating code beyond only standalone functions. By evaluating three code generation models on CoderEval, we find that the effectiveness of these models in generating standalone functions is substantially higher than that in generating non-standalone functions. Our analysis highlights the current progress and pinpoints future directions to further improve a model's effectiveness by leveraging contextual information for pragmatic code generation.

Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimization reproducible. SkillOpt is, to our knowledge, the first systematic controllable text-space optimizer for agent skills: a separate optimizer model turns scored rollouts into bounded add/delete/replace edits on a single skill document, and an edit is accepted only when it strictly improves a held-out validation score. A textual learning-rate budget, rejected-edit buffer, and epoch-wise slow/meta update make skill training stable while adding zero inference-time model calls at deployment. Across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt is best or tied on all 52 evaluated (model, benchmark, harness) cells and beats every per-cell competitor among human, one-shot LLM, Trace2Skill, TextGrad, GEPA, and EvoSkill skills. On GPT-5.5 it lifts the average no-skill accuracy by +23.5 points in direct chat, by +24.8 inside the Codex agentic loop, and by +19.1 inside Claude Code. Transfer experiments further show that optimized skill artifacts retain value when moved across model scales, between Codex and Claude Code execution environments, and to a nearby math benchmark without further optimization.

Large language models can generate code and call tools with remarkable fluency, yet deploying them as practical software engineering assistants still expose stubborn gaps: finite context windows, single mistakes that derail entire sessions, agents that get stuck in dead ends, AI slop, and generated changes that are difficult to review or revert. We present KISS Sorcar, a general-purpose assistant and integrated development environment (IDE) built on top of the KISS Agent Framework, a stupidly-simple AI agent framework of roughly 1,850 lines of code. The framework addresses these gaps using a robust system prompt and through a five-layer agent hierarchy in which each layer adds exactly one concern: budget-tracked ReAct execution, automatic continuation across sub-sessions via summarization, coding, and browser tools with parallel sub-agents, persistent multi-turn chat with history recall, and git worktree isolation so every task runs on its own branch. To assess the power of the KISS agent framework, we implemented KISS Sorcar as a free, open-source Visual Studio Code extension that runs locally and effectively for long-horizon tasks, and supports browser automation, multimodal input, and Docker containers. In this research, we deliberately prioritize output quality over latency: giving a frontier model adequate time to validate its own output -- running linters, type checkers, and tests -- dramatically reduces the low-quality code that plagues faster but less thorough agents. The entire system was built using itself in 4.5 months, providing a continuous stress test in which any agent-introduced bug immediately impairs its own ability to work. On Terminal Bench 2.0, KISS Sorcar achieves a 62.2% overall pass rate with Claude Opus 4.6, comparing favorably to Claude Code (58%) and Cursor Composer 2 (61.7).

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with BountyBench, we set up 25 systems with complex, real-world codebases. To capture the vulnerability lifecycle, we define three task types: Detect (detecting a new vulnerability), Exploit (exploiting a given vulnerability), and Patch (patching a given vulnerability). For Detect, we construct a new success indicator, which is general across vulnerability types and provides localized evaluation. We manually set up the environment for each system, including installing packages, setting up server(s), and hydrating database(s). We add 40 bug bounties, which are vulnerabilities with monetary awards from \10 to 30,485, covering 9 of the OWASP Top 10 Risks. To modulate task difficulty, we devise a new strategy based on information to guide detection, interpolating from identifying a zero day to exploiting a given vulnerability. We evaluate 10 agents: Claude Code, OpenAI Codex CLI with o3-high and o4-mini, and custom agents with o3-high, GPT-4.1, Gemini 2.5 Pro Preview, Claude 3.7 Sonnet Thinking, Qwen3 235B A22B, Llama 4 Maverick, and DeepSeek-R1. Given up to three attempts, the top-performing agents are Codex CLI: o3-high (12.5% on Detect, mapping to \3,720; 90% on Patch, mapping to 14,152), Custom Agent: Claude 3.7 Sonnet Thinking (67.5% on Exploit), and Codex CLI: o4-mini (90% on Patch, mapping to \$14,422). Codex CLI: o3-high, Codex CLI: o4-mini, and Claude Code are more capable at defense, achieving higher Patch scores of 90%, 90%, and 87.5%, compared to Exploit scores of 47.5%, 32.5%, and 57.5% respectively; while the custom agents are relatively balanced between offense and defense, achieving Exploit scores of 17.5-67.5% and Patch scores of 25-60%.

Large language models can generate plausible quantum code, but it is unclear whether they can reliably target the specific software development kit (SDK) version requested by the user. We study this problem as API drift and introduce quantum-api-drift, a benchmark for measuring version fidelity, defined here as execution success on the requested SDK version, cross-version compatibility, failure modes, and documentation-guided repair in LLM-generated quantum SDK code. We instantiate the benchmark with Qiskit, a representative quantum SDK that underwent substantial interface changes across v0.43, v1.3, and v2.0. We evaluate 17 models on 50 tasks with 3 samples per prompt, yielding 450 generated samples and 1,350 executions per model. Sixteen models are tested in a matched REST API setting with a 1024-token output cap, while GPT-5.4 (Codex CLI) is reported separately as a reference configuration. Across the 16 matched REST models, diagonal Pass@1 ranges from 0.02 to 0.85. Claude Opus 4.7 is strongest on v0.43 and v2.0, while Grok 4.20 is strongest on v1.3 at 0.513. Error profiles differ systematically by model strength: weaker models fail mainly with broken imports, while stronger models more often reach deprecation-level failures. Documentation-guided repair succeeds for 0.19 to 0.59 of repair attempts overall and is consistently much more effective for migration to v2.0 than to v1.3. The benchmark artifacts are publicly available at https://github.com/arasyi/quantum-api-drift. These results show that version alignment is a distinct evaluation axis for quantum code generation and that API drift remains only partly recoverable even with migration guidance.

Modern front-end (FE) development, especially when leveraging the unique features of frameworks like React and Vue, presents distinctive challenges. These include managing modular architectures, ensuring synchronization between data and visual outputs for declarative rendering, and adapting reusable components to various scenarios. Such complexities make it particularly difficult for state-of-the-art large vision-language models (VLMs) to generate accurate and functional code directly from design images. To address these challenges, we propose a reflective agentic workflow that synthesizes high-quality image-text data to capture the diverse characteristics of FE development. This workflow automates the extraction of self-containedA \textbf{self-contained code snippet is one that encapsulates all necessary logic, styling, and dependencies, ensuring it functions independently without requiring external imports or context.} code snippets from real-world projects, renders the corresponding visual outputs, and generates detailed descriptions that link design elements to functional code. To further expand the scope and utility of the synthesis, we introduce three data synthesis strategies: Evolution-based synthesis, which enables scalable and diverse dataset expansion; Waterfall-Model-based synthesis, which generates logically coherent code derived from system requirements; and Additive Development synthesis, which iteratively increases the complexity of human-authored components. We build a large vision-language model, Flame, trained on the synthesized datasets and demonstrate its effectiveness in generating React code via the pass@k metric. Our results suggest that a code VLM trained to interpret images before code generation may achieve better performance.

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the compiler. Inspired by this, we present ReflectionCoder, a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Furthermore, we propose reflection self-distillation and dynamically masked distillation to effectively utilize these reflection sequences. Extensive experiments on three benchmarks, i.e., HumanEval (+), MBPP (+), and MultiPl-E, demonstrate that models fine-tuned with our method achieve state-of-the-art performance. Notably, ReflectionCoder-DeepSeek-Coder-33B reaches pass@1 of 82.9 (76.8) on HumanEval (+) and 84.1 (72.0) on MBPP (+), on par with GPT-3.5-Turbo and Claude-3-opus, and surpasses early GPT-4. Beyond the code domain, we believe this approach can benefit other domains that focus on final results and require long reasoning paths. Code and data are available at https://github.com/SenseLLM/ReflectionCoder.

Agents powered by large language models (LLMs) are increasingly adopted in the software industry, contributing code as collaborators or even autonomous developers. As their presence grows, it becomes important to assess the current boundaries of their coding abilities. Existing agentic coding benchmarks, however, cover a limited task scope, e.g., bug fixing within a single pull request (PR), and often rely on non-executable evaluations or lack an automated approach for continually updating the evaluation coverage. To address such issues, we propose FeatureBench, a benchmark designed to evaluate agentic coding performance in end-to-end, feature-oriented software development. FeatureBench incorporates an execution-based evaluation protocol and a scalable test-driven method that automatically derives tasks from code repositories with minimal human effort. By tracing from unit tests along a dependency graph, our approach can identify feature-level coding tasks spanning multiple commits and PRs scattered across the development timeline, while ensuring the proper functioning of other features after the separation. Using this framework, we curated 200 challenging evaluation tasks and 3825 executable environments from 24 open-source repositories in the first version of our benchmark. Empirical evaluation reveals that the state-of-the-art agentic model, such as Claude 4.5 Opus, which achieves a 74.4% resolved rate on SWE-bench, succeeds on only 11.0% of tasks, opening new opportunities for advancing agentic coding. Moreover, benefiting from our automated task collection toolkit, FeatureBench can be easily scaled and updated over time to mitigate data leakage. The inherent verifiability of constructed environments also makes our method potentially valuable for agent training.

Understanding large codebases is a long-horizon task for Large Language Model (LLM) agents: answering a single question can require building and running the software, tracing execution across files, and synthesizing evidence over tens of minutes. On SWE-Atlas QnA, a benchmark of long-horizon questions over production repositories, a single Claude Code agent (Opus 4.6) resolves only 32.3% of tasks. Dividing the work among agents with clean contexts mitigates this limitation. However, the subtasks of code comprehension are interdependent. One agent's findings can rewrite another's task, so agents must coordinate during execution, not only at phase boundaries. Existing multi-agent systems support such exchange only between phases, through staged handoffs or synchronized rounds. Communication and work remain mutually exclusive. A discovery made mid-execution cannot be shared until the next boundary. We present AgentRadio, an asynchronous message-passing layer that equips coding-agent harnesses with three primitives: threads, messages, and waiting for mentions. The last runs as a background task, surfacing teammates' messages without interrupting foreground work, so each agent remains passively aware of its peers and folds new findings into its ongoing task. Under a five-phase protocol of division of labor and negotiation, four agents organized by AgentRadio resolve 62.1% of tasks, 29.8 points above a single agent and above Claude Code with the newer Opus 4.8 (57.2%). Rubric-level analysis shows the gain growing with task difficulty, consistent with mid-course correction as the underlying mechanism. Our code is available at https://github.com/Coral-Protocol/AgentRadio.

Despite their impressive performance on complex tasks, current language models (LMs) typically operate in a vacuum: Each input query is processed separately, without retaining insights from previous attempts. Here, we present Dynamic Cheatsheet (DC), a lightweight framework that endows a black-box LM with a persistent, evolving memory. Rather than repeatedly re-discovering or re-committing the same solutions and mistakes, DC enables models to store and reuse accumulated strategies, code snippets, and general problem-solving insights at inference time. This test-time learning enhances performance substantially across a range of tasks without needing explicit ground-truth labels or human feedback. Leveraging DC, Claude 3.5 Sonnet's accuracy more than doubled on AIME math exams once it began retaining algebraic insights across questions. Similarly, GPT-4o's success rate on Game of 24 increased from 10% to 99% after the model discovered and reused a Python-based solution. In tasks prone to arithmetic mistakes, such as balancing equations, DC enabled GPT-4o and Claude to reach near-perfect accuracy by recalling previously validated code, whereas their baselines stagnated around 50%. Beyond arithmetic challenges, DC yields notable accuracy gains on knowledge-demanding tasks. Claude achieved a 9% improvement in GPQA-Diamond and an 8% boost on MMLU-Pro problems. Crucially, DC's memory is self-curated, focusing on concise, transferable snippets rather than entire transcript. Unlike finetuning or static retrieval methods, DC adapts LMs' problem-solving skills on the fly, without modifying their underlying parameters. Overall, our findings present DC as a promising approach for augmenting LMs with persistent memory, bridging the divide between isolated inference events and the cumulative, experience-driven learning characteristic of human cognition.

AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published research has become both harder and more important. As manual replication is slow and expensive, a growing line of work uses coding agents to automate parts of the process. Existing efforts are largely packaged as benchmarks with companion agents that only run inside the benchmark's own pipeline, and no general-purpose replication tool exists. We present VERITAS, a domain-agnostic replication framework built around CLI coding agents. Given a paper, a code repository, or both, VERITAS extracts the paper's claims, runs the methodology while resolving issues as they arise, and judges each claim against the evidence from experiment runs. The pipeline returns an importance-weighted Replication Score, a severity-rated log of every fix applied, and the patched codebase. We evaluate VERITAS on CORE-Bench and ReplicationBench, 65 papers spanning computer science, social science, medicine, and astrophysics. Against two strong Claude Code baselines on the same model and host environment, VERITAS achieves state-of-the-art performance and leads on every metric on both benchmarks.

Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine the correctness of a solution, as a new scaling axis. To unlock this and demonstrate its effectiveness, we introduce LLM-as-a-Verifier, a general-purpose verification framework that provides fine-grained feedback for agentic tasks without requiring additional training. Unlike standard LM judges that prompt LLMs to produce discrete scores for candidate solutions, LLM-as-a-Verifier computes the expectation over the distribution of scoring token logits to generate continuous scores. This probabilistic formulation enables verification to scale along multiple dimensions: (1) score granularity, (2) repeated evaluation, and (3) criteria decomposition. In particular, we show that scaling the scoring granularity leads to better separation between positive and negative solutions, resulting in more calibrated comparisons. Moreover, scaling repeated evaluation and criteria decomposition consistently lead to additional gains in verification accuracy through variance and complexity reduction. We further introduce a cost-efficient ranking algorithm for selecting the best solution among candidates using the verifier's continuous scores. LLM-as-a-Verifier achieves state-of-the-art performance on Terminal-Bench V2 (86.5%), SWE-Bench Verified (78.2%), RoboRewardBench (87.4%), and MedAgentBench (73.3%). Beyond verification, the fine-grained signals from LLM-as-a-Verifier can also serve as a proxy for estimating task progress. We build an extension for Claude Code, enabling developers to monitor and improve their own agentic systems. Finally, we show that LLM-as-a-Verifier can provide dense feedback for RL, improving the sample efficiency of SAC and GRPO on robotics and mathematical reasoning benchmarks.

How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal-Bench 4.0, GPT-5.6 Sol with Codex resolves 37.3% of the tasks and Claude Opus 5 with Claude Code 51.8%. These tasks fail at the step from reaching a resource to applying it, which we call the last mile to the real world. Existing approaches put the resource within reach but leave the competence to apply it with the caller, so each harness rebuilds that competence. We introduce agent-native primitives, reusable units that equip a resource with a resident LLM that applies it in context and communicates with other primitives, and HEELO (Harness Engineering around Evolving Agent-Native Primitives for the Last Mile to Real-WOrld Tasks), a harness engineering framework that builds each task's harness from a library of such primitives. HEELO composes the primitives a task needs into a task-specific graph, verifies the result against evidence from the environment, revises the primitives a failure implicates, and admits new or improved primitives after validation. We instantiate HEELO with eight primitive families, each built for one kind of task, and evaluate them on more than twenty benchmarks. Dev-Primitives raise Terminal-Bench 4.0 resolution from 37.3% under Codex to 55.5% on the same backbone, Harness Primitives composed per task raise Terminal-Bench 2.0 Pass@1 from 60.0% for the seed harness to 72.2%, Tool Primitives raise ToolBench pass rate from 55.8% to 75.1%, and Navigation Primitives raise GAIA-Text-103 accuracy from 45.6% to 58.3%. On the 46 real-world tasks of our heelo.dev platform, Claude Opus 5.5 with Claude Code and GPT-6.1 Sol with Codex complete 9 each on their own and 39 and 35 when connected to HEELO through our MCP server, with 1.9times and 2.3times less time and 1.55times lower cost per completed task.

Computational Fluid Dynamics (CFD) is an essential simulation tool in engineering, yet its steep learning curve and complex manual setup create significant barriers. To address these challenges, we introduce Foam-Agent, a multi-agent framework that automates the entire end-to-end OpenFOAM workflow from a single natural language prompt. Our key innovations address critical gaps in existing systems: 1. An Comprehensive End-to-End Simulation Automation: Foam-Agent is the first system to manage the full simulation pipeline, including advanced pre-processing with a versatile Meshing Agent capable of handling external mesh files and generating new geometries via Gmsh, automatic generation of HPC submission scripts, and post-simulation visualization via ParaView. 2. Composable Service Architecture: Going beyond a monolithic agent, the framework uses Model Context Protocol (MCP) to expose its core functions as discrete, callable tools. This allows for flexible integration and use by other agentic systems, such as Claude-code, for more exploratory workflows. 3. High-Fidelity Configuration Generation: We achieve superior accuracy through a Hierarchical Multi-Index RAG for precise context retrieval and a dependency-aware generation process that ensures configuration consistency. Evaluated on a benchmark of 110 simulation tasks, Foam-Agent achieves an 88.2% success rate with Claude 3.5 Sonnet, significantly outperforming existing frameworks (55.5% for MetaOpenFOAM). Foam-Agent dramatically lowers the expertise barrier for CFD, demonstrating how specialized multi-agent systems can democratize complex scientific computing. The code is public at https://github.com/csml-rpi/Foam-Agent.

Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks typically begin with self-contained descriptions or predefined optimization tasks, underrepresenting the translation of original business materials into professionally validated solutions. We introduce OR-License, an end-to-end benchmark of 31 instances across 10 industrial scenarios from paid OR engagements totaling USD 3.68 million. It preserves original requirements, input data, deliverable formats, and information boundaries after de-identification. To study information acquisition, we introduce ORSim, a controlled client simulator that discloses business facts without supplying OR expertise. Hidden evaluation checks feasibility and compares objective quality against original expert solutions accepted by clients before benchmark construction. Deployment-Adjusted Quality (DAQ) averages expert-relative quality across instances, assigning zero to infeasible deliveries. Across 11 frontier LLMs using coding-agent harnesses, several exceed the expert reference in conditional objective quality, but none matches its DAQ; the strongest primary Claude Code configuration achieves 88.39% strict feasibility and a DAQ of 0.87 against the expert reference of 1. Client information acquisition extends beyond clarification into solution development and validation, with some later stages showing higher confirmed issue-resolution proportions. Trajectory analysis identifies formulation and implementation failures, while task-equalized research-chain completion rates range from 24% to 45% across models on evaluable tasks. These findings motivate sustained information-gap resolution, faithful problem formulation, and evidence-linked self-improvement for reliable long-horizon agents.

LLM-Agents have evolved into autonomous systems for complex task execution, with the SKILL.md specification emerging as a de facto standard for encapsulating agent capabilities. However, a critical bottleneck remains: different agent frameworks exhibit starkly different sensitivities to prompt formatting, causing up to 40% performance variation, yet nearly all skills exist as a single, format-agnostic Markdown version. Manual per-platform rewriting creates an unsustainable maintenance burden, while prior audits have found that over one third of community skills contain security vulnerabilities. To address this, we present SkCC, a compilation framework that introduces classical compiler design into agent skill development. At its core, SkIR - a strongly-typed intermediate representation - decouples skill semantics from platform-specific formatting, enabling portable deployment across heterogeneous agent frameworks. Around this IR, a compile-time Analyzer enforces security constraints via Anti-Skill Injection before deployment. Through a four-phase pipeline, SkCC reduces adaptation complexity from O(m times n) to O(m + n). Experiments on SkillsBench demonstrate that compiled skills consistently outperform their original counterparts, improving pass rates from 21.1% to 33.3% on Claude Code and from 35.1% to 48.7% on Kimi CLI, while achieving sub-10ms compilation latency, a 94.8% proactive security trigger rate, and 10-46% runtime token savings across platforms.

Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting falls short of representing the real-world software development scenario where repositories span multiple files with numerous cross-file dependencies, and accessing and understanding cross-file context is often required to complete the code correctly. To fill in this gap, we propose CrossCodeEval, a diverse and multilingual code completion benchmark that necessitates an in-depth cross-file contextual understanding to complete the code accurately. CrossCodeEval is built on a diverse set of real-world, open-sourced, permissively-licensed repositories in four popular programming languages: Python, Java, TypeScript, and C#. To create examples that strictly require cross-file context for accurate completion, we propose a straightforward yet efficient static-analysis-based approach to pinpoint the use of cross-file context within the current file. Extensive experiments on state-of-the-art code language models like CodeGen and StarCoder demonstrate that CrossCodeEval is extremely challenging when the relevant cross-file context is absent, and we see clear improvements when adding these context into the prompt. However, despite such improvements, the pinnacle of performance remains notably unattained even with the highest-performing model, indicating that CrossCodeEval is also capable of assessing model's capability in leveraging extensive context to make better code completion. Finally, we benchmarked various methods in retrieving cross-file context, and show that CrossCodeEval can also be used to measure the capability of code retrievers.

General-purpose automated software engineering (ASE) includes tasks such as code completion, retrieval, repair, QA, and summarization. These tasks require a code retrieval system that can handle specific queries about code entities, or code entity queries (for example, locating a specific class or retrieving the dependencies of a function), as well as general queries without explicit code entities, or natural language queries (for example, describing a task and retrieving the corresponding code). We present RANGER, a repository-level code retrieval agent designed to address both query types, filling a gap in recent works that have focused primarily on code-entity queries. We first present a tool that constructs a comprehensive knowledge graph of the entire repository, capturing hierarchical and cross-file dependencies down to the variable level, and augments graph nodes with textual descriptions and embeddings to bridge the gap between code and natural language. RANGER then operates on this graph through a dual-stage retrieval pipeline. Entity-based queries are answered through fast Cypher lookups, while natural language queries are handled by MCTS-guided graph exploration. We evaluate RANGER across four diverse benchmarks that represent core ASE tasks including code search, question answering, cross-file dependency retrieval, and repository-level code completion. On CodeSearchNet and RepoQA it outperforms retrieval baselines that use embeddings from strong models such as Qwen3-8B. On RepoBench, it achieves superior cross-file dependency retrieval over baselines, and on CrossCodeEval, pairing RANGER with BM25 delivers the highest exact match rate in code completion compared to other RAG methods.

How are AI assistants being used in the real world? While model providers in theory have a window into this impact via their users' data, both privacy concerns and practical challenges have made analyzing this data difficult. To address these issues, we present Clio (Claude insights and observations), a privacy-preserving platform that uses AI assistants themselves to analyze and surface aggregated usage patterns across millions of conversations, without the need for human reviewers to read raw conversations. We validate this can be done with a high degree of accuracy and privacy by conducting extensive evaluations. We demonstrate Clio's usefulness in two broad ways. First, we share insights about how models are being used in the real world from one million Claude.ai Free and Pro conversations, ranging from providing advice on hairstyles to providing guidance on Git operations and concepts. We also identify the most common high-level use cases on Claude.ai (coding, writing, and research tasks) as well as patterns that differ across languages (e.g., conversations in Japanese discuss elder care and aging populations at higher-than-typical rates). Second, we use Clio to make our systems safer by identifying coordinated attempts to abuse our systems, monitoring for unknown unknowns during critical periods like launches of new capabilities or major world events, and improving our existing monitoring systems. We also discuss the limitations of our approach, as well as risks and ethical concerns. By enabling analysis of real-world AI usage, Clio provides a scalable platform for empirically grounded AI safety and governance.

Code summarization is a critical task in natural language processing and software engineering, which aims to generate concise descriptions of source code. Recent advancements have improved the quality of these summaries, enhancing code readability and maintainability. However, the content of a repository or a class has not been considered in function code summarization. This study investigated the effectiveness of code summarization models beyond the function level, exploring the impact of class and repository contexts on the summary quality. The study involved revising benchmarks for evaluating models at class and repository levels, assessing baseline models, and evaluating LLMs with in-context learning to determine the enhancement of summary quality with additional context. The findings revealed that the fine-tuned state-of-the-art CodeT5+ base model excelled in code summarization, while incorporating few-shot learning and retrieved code chunks from RAG significantly enhanced the performance of LLMs in this task. Notably, the Deepseek Coder 1.3B and Starcoder2 15B models demonstrated substantial improvements in metrics such as BLEURT, METEOR, and BLEU-4 at both class and repository levels. Repository-level summarization exhibited promising potential but necessitates significant computational resources and gains from the inclusion of structured context. Lastly, we employed the recent SIDE code summarization metric in our evaluation. This study contributes to refining strategies for prompt engineering, few-shot learning, and RAG, addressing gaps in benchmarks for code summarization at various levels. Finally, we publish all study details, code, datasets, and results of evaluation in the GitHub repository available at https://github.com/kilimanj4r0/code-summarization-beyond-function-level.

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like responses, leading to their integration across diverse domains, including consulting and information retrieval. However, their widespread deployment also introduces substantial security risks, most notably in the form of prompt injection and jailbreak attacks. To systematically evaluate LLM vulnerabilities -- particularly to external prompt injection -- we conducted a series of experiments on eight commercial models. Each model was tested without supplementary sanitization, relying solely on its built-in safeguards. The results exposed exploitable weaknesses and emphasized the need for stronger security measures. Four categories of attacks were examined: direct injection, indirect (external) injection, image-based injection, and prompt leakage. Comparative analysis indicated that Claude 3 demonstrated relatively greater robustness; nevertheless, empirical findings confirm that additional defenses, such as input normalization, remain necessary to achieve reliable protection.

Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain benchmark comprising 300 end-to-end scientific workflows. In this paper, we release and evaluate 97 of these tasks, spanning quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment. Each task provides fixed inputs and specifies a bundle of required scientific deliverables. We evaluate twelve frontier models with three agent scaffolds. Pass Rate measures the fraction of tasks satisfying the full-completion criterion, while Avg. Score captures partial progress. Each of the best-performing configurations completed only 20 of the 97 released tasks, yielding a Pass Rate of 20.6%. Partial progress translated especially poorly into complete delivery in analytical chemistry and electrochemistry/environment: Avg. Scores reached 87.6 and 94.9, but the highest Pass Rates were only 4% and 0%. Among non-passing Claude Code trajectories, 75.5% still ended with language claiming completion. These findings show that neither high partial scores nor confident claims of completion reliably indicate that a scientific task has been fully delivered, highlighting the need to evaluate end-to-end workflow execution and the completeness of scientific deliverables together.

A simulation of a real robot workspace must preserve task-relevant interactions, while policies developed in it must operate on observations available to the real robot. Yet scene reconstruction and policy development are often treated separately. We present Agentic Real-to-Sim-to-Real (Agentic RSR), a framework that links scene reconstruction, policy development, and real-robot execution through the same manipulation task. Given a workspace video, a task description, and a known robot model, an agent recovers metric scale, iteratively refines the scene using visual feedback, and checks task-relevant interactions in MuJoCo. A coding agent then develops an executable policy, progressing from privileged object poses to visual observations and randomized simulation. The policy can interleave multiple observations and actions within one invocation, while the agent uses execution feedback to continue, retry, or revise its approach. A shared task-level interface carries the policy and accumulated experience to the real robot, where fresh observations and safety checks guide execution. Using Claude Opus 5.5 through DeepSeek Harness (DSH), all 18 scenes across two robots pass the joint visual check; mean four-view Depth MAE against reference depth estimates is 0.0808 m, mean Lab ΔE_{76} is 8.01, and mean grayscale SSIM is 0.7338. In real-robot experiments, the aggregate task success rate reaches 80% of the simulation task success rate, indicating substantial retention of simulated performance on hardware. Code and reconstructed scene data will be made publicly available.

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.

Large Language Models (LLMs) have shown promise in software engineering tasks, but evaluating their effectiveness in vulnerability detection is challenging due to the lack of high-quality datasets. Most existing datasets are limited to function-level labels, ignoring finer-grained vulnerability patterns and crucial contextual information. Also, poor data quality such as mislabeling, inconsistent annotations, and duplicates can lead to inflated performance and weak generalization. Moreover, by including only the functions, these datasets miss broader program context, like data/control dependencies and interprocedural interactions, that are essential for accurately understanding real-world security flaws. Without this context, detection models are evaluated under unrealistic assumptions. To address these limitations, this paper introduces SecVulEval, a benchmark designed to support fine-grained evaluation of LLMs and other detection methods with rich contextual information. SecVulEval focuses on real-world C/C++ vulnerabilities at the statement level. This granularity enables more precise evaluation of a model's ability to localize vulnerabilities, beyond simple binary classification at the function level. By incorporating rich contextual information, SecVulEval sets a new standard for vulnerability detection benchmarks in realistic scenarios. This benchmark includes 25,440 function samples covering 5,867 unique CVEs in C/C++ projects from 1999 to 2024. We evaluated the SOTA LLMs with a multi-agent-based approach. The evaluation on our dataset shows that the models are still far from accurately predicting vulnerable statements in a given function. The best-performing Claude-3.7-Sonnet model achieves 23.83% F1-score for detecting vulnerable statements with correct reasoning. Finally, we analyze the LLM outputs and provide insights into their behavior in vulnerability detection for C/C++.

The performance of large language model (LLM) systems depends not only on model weights, but also on their harness: the code that determines what information to store, retrieve, and present to the model. Yet harnesses are still designed largely by hand, and existing text optimizers are poorly matched to this setting because they compress feedback too aggressively. We introduce Meta-Harness, an outer-loop system that searches over harness code for LLM applications. It uses an agentic proposer that accesses the source code, scores, and execution traces of all prior candidates through a filesystem. On online text classification, Meta-Harness improves over a state-of-the-art context management system by 7.7 points while using 4x fewer context tokens. On retrieval-augmented math reasoning, a single discovered harness improves accuracy on 200 IMO-level problems by 4.7 points on average across five held-out models. On agentic coding, discovered harnesses surpass the best hand-engineered baselines on TerminalBench-2. Together, these results show that richer access to prior experience can enable automated harness engineering.

Natural language image-caption datasets, widely used for training Large Multimodal Models, mainly focus on natural scenarios and overlook the intricate details of mathematical figures that are critical for problem-solving, hindering the advancement of current LMMs in multimodal mathematical reasoning. To this end, we propose leveraging code as supervision for cross-modal alignment, since code inherently encodes all information needed to generate corresponding figures, establishing a precise connection between the two modalities. Specifically, we co-develop our image-to-code model and dataset with model-in-the-loop approach, resulting in an image-to-code model, FigCodifier and ImgCode-8.6M dataset, the largest image-code dataset to date. Furthermore, we utilize FigCodifier to synthesize novel mathematical figures and then construct MM-MathInstruct-3M, a high-quality multimodal math instruction fine-tuning dataset. Finally, we present MathCoder-VL, trained with ImgCode-8.6M for cross-modal alignment and subsequently fine-tuned on MM-MathInstruct-3M for multimodal math problem solving. Our model achieves a new open-source SOTA across all six metrics. Notably, it surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%. The dataset and models will be released at https://github.com/mathllm/MathCoder.

LLM-based code agents treat repositories as unstructured text, applying edits through brittle string matching that frequently fails due to formatting drift or ambiguous patterns. We propose reframing the codebase as a structured action space where agents operate on named AST entities rather than text spans. Our framework, CODESTRUCT, provides readCode for retrieving complete syntactic units and editCode for applying syntax-validated transformations to semantic program elements. Evaluated on SWE-Bench Verified across six LLMs, CODESTRUCT improves Pass@1 accuracy by 1.2-5.0% while reducing token consumption by 12-38% for most models. Models that frequently fail to produce valid patches under text-based interfaces benefit most: GPT-5-nano improves by 20.8% as empty-patch failures drop from 46.6% to 7.2%. On CodeAssistBench, we observe consistent accuracy gains (+0.8-4.4%) with cost reductions up to 33%. Our results show that structure-aware interfaces offer a more reliable foundation for code agents.

This paper presents a novel framework for automated code generation and debugging, designed to improve accuracy, efficiency, and scalability in software development. The proposed system integrates three core components LangGraph, GLM4 Flash, and ChromaDB within a four step iterative workflow to deliver robust performance and seamless functionality. LangGraph serves as a graph-based library for orchestrating tasks, providing precise control and execution while maintaining a unified state object for dynamic updates and consistency. It supports multi-agent, hierarchical, and sequential processes, making it highly adaptable to complex software engineering workflows. GLM4 Flash, a large language model, leverages its advanced capabilities in natural language understanding, contextual reasoning, and multilingual support to generate accurate code snippets based on user prompts. ChromaDB acts as a vector database for semantic search and contextual memory storage, enabling the identification of patterns and the generation of context-aware bug fixes based on historical data. The system operates through a structured four-step process: (1) Code Generation, which translates natural language descriptions into executable code; (2) Code Execution, which validates the code by identifying runtime errors and inconsistencies; (3) Code Repair, which iteratively refines buggy code using ChromaDB's memory capabilities and LangGraph's state tracking; and (4) Code Update, which ensures the code meets functional and performance requirements through iterative modifications.

Developers often dedicate significant time to maintaining and refactoring existing code. However, most prior work on generative models for code focuses solely on creating new code, overlooking the distinctive needs of editing existing code. In this work, we explore a multi-round code auto-editing setting, aiming to predict edits to a code region based on recent changes within the same codebase. Our model, Coeditor, is a fine-tuned language model specifically designed for code editing tasks. We represent code changes using a line diff format and employ static analysis to form large customized model contexts, ensuring the availability of appropriate information for prediction. We collect a code editing dataset from the commit histories of 1650 open-source Python projects for training and evaluation. In a simplified single-round, single-edit task, Coeditor significantly outperforms GPT-3.5 and SOTA open-source code completion models (bringing exact-match accuracy from 34.7 up to 60.4), demonstrating the benefits of incorporating editing history for code completion. In a multi-round, multi-edit setting, we observe substantial gains by iteratively conditioning on additional user edits. We have open-sourced our code, data, and model weights to encourage future research and have released a VSCode extension powered by our model for interactive IDE usage.

Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models. In the area of code synthesis, the commonly used evaluation metric is BLEU or perfect accuracy, but they are not suitable enough to evaluate codes, because BLEU is originally designed to evaluate the natural language, neglecting important syntactic and semantic features of codes, and perfect accuracy is too strict thus it underestimates different outputs with the same semantic logic. To remedy this, we introduce a new automatic evaluation metric, dubbed CodeBLEU. It absorbs the strength of BLEU in the n-gram match and further injects code syntax via abstract syntax trees (AST) and code semantics via data-flow. We conduct experiments by evaluating the correlation coefficient between CodeBLEU and quality scores assigned by the programmers on three code synthesis tasks, i.e., text-to-code, code translation, and code refinement. Experimental results show that our proposed CodeBLEU can achieve a better correlation with programmer assigned scores compared with BLEU and accuracy.

Retrieval-Augmented Generation (RAG) frameworks aim to enhance Code Language Models (CLMs) by including another module for retrieving relevant context to construct the input prompt. However, these retrieval modules commonly use semantic search, requiring substantial computational resources for training and hosting these embedded models, making them infeasible to integrate into lightweight applications such as in-IDE AI-based code completion. In this solution paper, we prove that using keyword-search is sufficient to retrieve relevant and useful code context inside large codebases, without the need for extensive GPU resources. The usefulness of code contexts found by our solution is demonstrated through their completion results on the Code Context Competition's benchmark, reaching 0.748 and 0.725 chRF scores on Kotlin and Python tracks, respectively.

We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared vocabulary. A fast, inexpensive draft model generates a candidate response; a capable verify model accepts, enhances, or is bypassed entirely depending on a lightweight complexity router. On a real-world agentic coding workload (Claude Code), RLM-Cascade achieves a draft-use rate of 88.8% across 125 production requests, reducing API cost by 45.8% relative to a direct Opus baseline. Counter-intuitively, the proxy also reduces end-to-end latency: median response time is 2,026 ms versus 3,698 ms for Native Opus -- a 1.83X speedup at p50 -- because the SKIPPED path (DeepSeek only, no Opus call) dominates the workload distribution. Quality matches or exceeds the Opus baseline: 100% pass rate on a 20-task Code/Math/Instruct benchmark versus 95% for Native Opus. We further describe a rule-based complexity router that selects the SKIPPED path for simple agentic turns and a hybrid tool-call strategy that bypasses the speculative pipeline for schema-critical tool-selection turns. RLM-Cascade is deployed in production as an enterprise AI infrastructure component and published as open source with a live metrics dashboard and Prometheus endpoint.

The adoption of AI-powered code completion tools in software development has increased substantially, yet the user interaction data produced by these systems remain proprietary within large corporations. This creates a barrier for the academic community, as researchers must often develop dedicated platforms to conduct studies on human--AI interaction, making reproducible research and large-scale data analysis impractical. In this work, we introduce Code4MeV2, a research-oriented, open-source code completion plugin for JetBrains IDEs, as a solution to this limitation. Code4MeV2 is designed using a client--server architecture and features inline code completion and a context-aware chat assistant. Its core contribution is a modular and transparent data collection framework that gives researchers fine-grained control over telemetry and context gathering. Code4MeV2 achieves industry-comparable performance in terms of code completion, with an average latency of 200~ms. We assess our tool through a combination of an expert evaluation and a user study with eight participants. Feedback from both researchers and daily users highlights its informativeness and usefulness. We invite the community to adopt and contribute to this tool. More information about the tool can be found at https://app.code4me.me.

We present SuperCoder2.0, an advanced autonomous system designed to enhance software development through artificial intelligence. The system combines an AI-native development approach with intelligent agents to enable fully autonomous coding. Key focus areas include a retry mechanism with error output traceback, comprehensive code rewriting and replacement using Abstract Syntax Tree (ast) parsing to minimize linting issues, code embedding technique for retrieval-augmented generation, and a focus on localizing methods for problem-solving rather than identifying specific line numbers. The methodology employs a three-step hierarchical search space reduction approach for code base navigation and bug localization:utilizing Retrieval Augmented Generation (RAG) and a Repository File Level Map to identify candidate files, (2) narrowing down to the most relevant files using a File Level Schematic Map, and (3) extracting 'relevant locations' within these files. Code editing is performed through a two-part module comprising CodeGeneration and CodeEditing, which generates multiple solutions at different temperature values and replaces entire methods or classes to maintain code integrity. A feedback loop executes repository-level test cases to validate and refine solutions. Experiments conducted on the SWE-bench Lite dataset demonstrate SuperCoder2.0's effectiveness, achieving correct file localization in 84.33% of cases within the top 5 candidates and successfully resolving 34% of test instances. This performance places SuperCoder2.0 fourth globally on the SWE-bench leaderboard. The system's ability to handle diverse repositories and problem types highlights its potential as a versatile tool for autonomous software development. Future work will focus on refining the code editing process and exploring advanced embedding models for improved natural language to code mapping.

The impressive performance of large language models (LLMs) on code-related tasks has shown the potential of fully automated software development. In light of this, we introduce a new software engineering task, namely Natural Language to code Repository (NL2Repo). This task aims to generate an entire code repository from its natural language requirements. To address this task, we propose a simple yet effective framework CodeS, which decomposes NL2Repo into multiple sub-tasks by a multi-layer sketch. Specifically, CodeS includes three modules: RepoSketcher, FileSketcher, and SketchFiller. RepoSketcher first generates a repository's directory structure for given requirements; FileSketcher then generates a file sketch for each file in the generated structure; SketchFiller finally fills in the details for each function in the generated file sketch. To rigorously assess CodeS on the NL2Repo task, we carry out evaluations through both automated benchmarking and manual feedback analysis. For benchmark-based evaluation, we craft a repository-oriented benchmark, SketchEval, and design an evaluation metric, SketchBLEU. For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies. Extensive experiments prove the effectiveness and practicality of CodeS on the NL2Repo task.

Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge requires understanding real workload patterns, yet the data needed for such analysis is largely absent. Existing public traces and benchmarks do not capture real, day-to-day coding-agent usage across multiple agents and model families for serving-system analysis. To help fill this gap, we collect and release a trace of roughly 4,300 coding-agent sessions, containing about 350,000 LLM steps and 430,000 tool calls from our own day-to-day use of Claude Code and Codex. Our analysis shows that coding-agent workloads feature long autonomous loops, long contexts with short outputs, diverse and heavily-tailed tool calls, and high but imperfect prefix cache hit rates. These findings point to concrete opportunities for optimizing serving, including lower-overhead tool calling, append-length-aware prefill, semantic-aware tool-latency prediction, and improved KV-cache management around human-paced gaps. We release the dataset, trace collection pipeline, and analysis code at https://github.com/uw-syfi/TraceLab.git the project website is https://tracelab.cs.washington.edu.

Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from scientific Python repositories on GitHub, each paired with expert-authored patches and, on average, 264.6 community-maintained performance workloads per task, enabling the holistic ability of LLM agents to optimize codebases under realistic correctness and performance constraints. Our evaluations reveal that repository-scale, multi-objective optimization remains a major challenge for frontier LLM agents. Project website at: https://formula-code.github.io

Fill-in-the-Middle (FIM) models play a vital role in code completion tasks, leveraging both prefix and suffix context to provide more accurate and contextually relevant suggestions. This paper presents approaches to improve FIM code completion while addressing the challenge of maintaining low latency for real-time coding assistance. We enhance FIM code completion by incorporating context and curriculum examples in the training process. We identify patterns where completion suggestions fail more frequently, revealing complexities that smaller language models struggle with. To address these challenges, we develop a curriculum dataset by extracting hard-to-complete patterns from code repositories and generate context examples using semantic and static analysis tools (e.g. TSC compiler). We fine-tune various sized models, including StarCoder and DeepSeek, on this enhanced dataset. Our evaluation encompasses three key dimensions: the Santa Coder FIM task, the Amazon CCEval benchmark, and a new Multi-Line Infilling evaluation benchmark derived from SWE-bench. Comprehensive ablation studies across multiple model sizes reveal that while all fine-tuned models show improvements, the performance gains are more pronounced for smaller parameter models and incorporating difficult-to-complete examples, as part of curriculum learning, improves the code completion performance. This finding is particularly significant given the latency constraints of code completion tasks. While larger models like GPT and Claude perform well in multi-line completions but are prohibitively challenging to use given high latency, and our fine-tuned models achieve a balance between performance and latency. Finally, we validate our approach through online A/B testing, demonstrating tangible improvements in Completion Acceptance Rate (CAR) and Completion Persistence Rate (CPR), with zero latency impact.

Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized. We present HarnessSecurity, the first systematic empirical study and benchmark of open- and closed-source coding agent harnesses. First, we derive a ten-mechanism taxonomy and then assess 400 harness-mechanism cells using independent ratings by researchers and large language model (LLM) judges. We find that about half of confirmed mechanism implementations are opt-in, while closed-source harnesses exhibit substantial evidence gaps. Second, we introduce HarnessSecurity-Bench, a benchmark of 23 tasks across five attack surfaces without sacrificing legitimate task requirements. Using separate deterministic oracles to measure task utility and attack effects with security setting comparisons, we evaluate nine mechanisms across six leading harnesses: Claude Code, Codex CLI, Gemini CLI, gptme, Qwen Code, and GitHub Copilot. Under a controlled LLM baseline GLM-5.2, we conduct 2,500 trials, recording 81,155 tool calls and over 2.2 billion tokens. Enabling auto-approve increases utility and raises attack success from 29.2% to 95.6%. Network isolation and read-only mode reduce attack effects with substantial utility losses, while command allowlisting and command denylisting reduce attack effects with a small utility loss and a utility gain, respectively. Task-level cases show that restrictions on a shared capability can obstruct both legitimate and malicious operations, and that allowed tools or commands can leave unauthorized operations reachable through alternative execution paths. Harness providers should make security settings verifiable, test alternative execution paths to protected operations, and assess attack effects alongside task utility and execution costs.

The harness surrounding a language model is a central determinant of agent performance. Recent methods optimize harnesses by searching over complete programs, where individual mechanisms are difficult to isolate and reuse. We introduce PluginRSI, which represents a harness as a composition of atomized plugins and organizes harness evolution around these plugins. Individual plugins are improved independently and accumulated in a shared library, then recombined into new harnesses at each iteration. PluginRSI improves over existing harness optimization methods across software engineering, command-line interaction, and question-answering tasks. The resulting harnesses retain their advantage when transferred to other solver models without further optimization. The evolved plugin library accelerates subsequent optimization from the initial harness, which helps faster and higher convergence on unseen tasks. These results show that accumulating reusable mechanisms provides an effective basis for continued harness improvement.

Despite the huge success of Large Language Models (LLMs) in coding assistants like GitHub Copilot, these models struggle to understand the context present in the repository (e.g., imports, parent classes, files with similar names, etc.), thereby producing inaccurate code completions. This effect is more pronounced when using these assistants for repositories that the model has not seen during training, such as proprietary software or work-in-progress code projects. Recent work has shown the promise of using context from the repository during inference. In this work, we extend this idea and propose RepoFusion, a framework to train models to incorporate relevant repository context. Experiments on single-line code completion show that our models trained with repository context significantly outperform much larger code models as CodeGen-16B-multi (sim73times larger) and closely match the performance of the sim 70times larger StarCoderBase model that was trained with the Fill-in-the-Middle objective. We find these results to be a novel and compelling demonstration of the gains that training with repository context can bring. We carry out extensive ablation studies to investigate the impact of design choices such as context type, number of contexts, context length, and initialization within our framework. Lastly, we release Stack-Repo, a dataset of 200 Java repositories with permissive licenses and near-deduplicated files that are augmented with three types of repository contexts. Additionally, we are making available the code and trained checkpoints for our work. Our released resources can be found at https://huggingface.co/RepoFusion.

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language Models (LLMs) integrated with external tools, file systems, and shell access through protocols like the Model Context Protocol (MCP). However, this expanded capability surface introduces critical security vulnerabilities. In this Systematization of Knowledge (SoK) paper, we present a comprehensive analysis of prompt injection attacks targeting agentic coding assistants. We propose a novel three-dimensional taxonomy categorizing attacks across delivery vectors, attack modalities, and propagation behaviors. Our meta-analysis synthesizes findings from 78 recent studies (2021--2026), consolidating evidence that attack success rates against state-of-the-art defenses exceed 85\% when adaptive attack strategies are employed. We systematically catalog 42 distinct attack techniques spanning input manipulation, tool poisoning, protocol exploitation, multimodal injection, and cross-origin context poisoning. Through critical analysis of 18 defense mechanisms reported in prior work, we identify that most achieve less than 50\% mitigation against sophisticated adaptive attacks. We contribute: (1) a unified taxonomy bridging disparate attack classifications, (2) the first systematic analysis of skill-based architecture vulnerabilities with concrete exploit chains, and (3) a defense-in-depth framework grounded in the limitations we identify. Our findings indicate that the security community must treat prompt injection as a first-class vulnerability class requiring architectural-level mitigations rather than ad-hoc filtering approaches.

Agentic systems have recently become the dominant paradigm for formal theorem proving, achieving strong performance by coordinating multiple models and tools. However, existing approaches often rely on task-specific pipelines and trained formal provers, limiting their flexibility and reproducibility. In this paper, we propose the paradigm that directly uses a general coding agent as a formal math reasoner. This paradigm is motivated by (1) A general coding agent provides a natural interface for diverse reasoning tasks beyond proving, (2) Performance can be improved by simply replacing the underlying base model, without training, and (3) MCP enables flexible extension and autonomous calling of specialized tools, avoiding complex design. Based on this paradigm, we introduce Numina-Lean-Agent, which combines Claude Code with Numina-Lean-MCP to enable autonomous interaction with Lean, retrieval of relevant theorems, informal proving and auxiliary reasoning tools. Using Claude Opus 4.5 as the base model, Numina-Lean-Agent solves all problems in Putnam 2025 (12 / 12), matching the best closed-source system. Beyond benchmark evaluation, we further demonstrate its generality by interacting with mathematicians to successfully formalize the Brascamp-Lieb theorem. We release Numina-Lean-Agent and all solutions at https://github.com/project-numina/numina-lean-agent.

Computer-aided design (CAD) is the backbone of modern industrial design, yet learned CAD generators still fall short of real engineering pipelines: they neither iterate like engineers nor evaluate what engineering requires. Prior work has treated CAD generation as two disjoint steps, part synthesis and assembly, where the former is graded by proximity to a gold reference and the latter, when handled at all, is reduced to a separate constraint solving step. In this work, we introduce a more industry-native task formulation that requires a model to produce a fully assembled multi-part STEP file from a free-form engineering brief, which is then validated via finite element analysis (FEA). FEA validation reveals that Codex (GPT-5.5) and Claude Code (Opus-4.7) agents do not produce a single strict-passing artifact in the main first-attempt sweep, with the best configuration meeting only about 20% of typed requirements on average. Moreover, we introduce two additional supervision signals, a novel text-only blueprint schema and a 21-view image renderer that aids the agent's visual inspection, that better align the generation loop with how engineers iterate in practice. On S2O and Fusion360, the same feedback tools improve geometric reconstruction, with GPT-5.5/xhigh rising from 0.444 to 0.592 Box-IoU on S2O and from 0.397 to 0.505 on Fusion360. Together these signals move CAD programs toward artifacts that are not only visually plausible but also checked against physical and structural requirements.

The recently introduced Mojo programming language (PL) by Modular, has received significant attention in the scientific community due to its claimed significant speed boost over Python. Despite advancements in code Large Language Models (LLMs) across various PLs, Mojo remains unexplored in this context. To address this gap, we introduce MojoBench, the first framework for Mojo code generation. MojoBench includes HumanEval-Mojo, a benchmark dataset designed for evaluating code LLMs on Mojo, and Mojo-Coder, the first LLM pretrained and finetuned for Mojo code generation, which supports instructions in 5 natural languages (NLs). Our results show that Mojo-Coder achieves a 30-35% performance improvement over leading models like GPT-4o and Claude-3.5-Sonnet. Furthermore, we provide insights into LLM behavior with underrepresented and unseen PLs, offering potential strategies for enhancing model adaptability. MojoBench contributes to our understanding of LLM capabilities and limitations in emerging programming paradigms fostering more robust code generation systems.

Recent advancements in code-fluent Large Language Models (LLMs) enabled the research on repository-level code editing. In such tasks, the model navigates and modifies the entire codebase of a project according to request. Hence, such tasks require efficient context retrieval, i.e., navigating vast codebases to gather relevant context. Despite the recognized importance of context retrieval, existing studies tend to approach repository-level coding tasks in an end-to-end manner, rendering the impact of individual components within these complicated systems unclear. In this work, we decouple the task of context retrieval from the other components of the repository-level code editing pipelines. We lay the groundwork to define the strengths and weaknesses of this component and the role that reasoning plays in it by conducting experiments that focus solely on context retrieval. We conclude that while the reasoning helps to improve the precision of the gathered context, it still lacks the ability to identify its sufficiency. We also outline the ultimate role of the specialized tools in the process of context gathering. The code supplementing this paper is available at https://github.com/JetBrains-Research/ai-agents-code-editing.

The performance of automatic code documentation generation models depends critically on the quality of the training data used for supervision. However, most existing code documentation datasets are constructed through large scale scraping of public repositories with limited quality control. As a result, they often contain noisy documentation, extensive duplication, and increasing contamination from AI generated content. These issues weaken the supervision signal available to learning-based models and complicate evaluation. We introduce Code2Doc, a quality-first curated dataset for function-level code documentation generation. Code2Doc consists of 13,358 high-quality function-documentation pairs extracted from widely used open-source repositories spanning five programming languages: Python, Java, TypeScript, JavaScript, and C++. The dataset is constructed using a four-stage curation pipeline that enforces documentation completeness and clarity, filters functions based on structural and complexity criteria, removes exact and near-duplicate code, and identifies documentation likely to be AI generated. Starting from 52,069 extracted candidates, only 25.6% satisfy all quality constraints. We provide a detailed analysis of the resulting dataset, which achieves a mean documentation quality score of 6.93 out of 10. Overall, 86.9% of samples contain explicit type annotations, and only 2.9% are flagged as potentially AI generated. Baseline experiments show that fine-tuning a large language model on Code2Doc yields relative improvements of 29.47% in BLEU and 24.04% in ROUGE-L over zero shot performance, despite the modest dataset size. We release both the dataset and the full curation pipeline to support reproducible research on automatic code documentation generation.

Context: The software maintenance phase involves many activities such as code refactoring, bug fixing, code review or testing. Program comprehension is key to all these activities, as it demands developers to grasp the knowledge (e.g., implementation details) required to modify the codebase. Methods as main building blocks in a program can offer developers this knowledge source for code comprehension. However, reading entire method statements can be challenging, which necessitates precise and up-to-date comments. Objective: We propose a solution as an IntelliJ IDEA plugin, named SmartDoc, that assists developers in generating context-aware method comments. Method: This plugin acts as an Artificial Intelligence (AI) agent that has its own memory and is augmented by target methods' context. When a request is initiated by the end-user, the method content and all its nested method calls are used in the comment generation. At the beginning, these nested methods are visited and a call graph is generated. This graph is then traversed using depth-first search (DFS), enabling the provision of full-context to enrich Large Language Model (LLM) prompts. Result: The product is a software, as a plugin, developed for Java codebase and installable on IntelliJ IDEA. This plugin can serve concurrently for methods whose comments are being updated , and it shares memory across all flows to avoid redundant calls. o measure the accuracy of this solution, a dedicated test case is run to record SmartDoc generated comments and their corresponding ground truth. For each collected result-set, three metrics are computed, BERTScore, BLEU and ROUGE-1. These metrics will determine how accurate the generated comments are in comparison to the ground truth. Result: The obtained accuracy, in terms of the precision, recall and F1, is promising, and lies in the range of 0.80 to 0.90 for BERTScore.

As the use of large language models (LLMs) for code generation becomes more prevalent in software development, it is critical to enhance both the efficiency and correctness of the generated code. Existing methods and models primarily focus on the correctness of LLM-generated code, ignoring efficiency. In this work, we present Effi-Code, an approach to enhancing code generation in LLMs that can improve both efficiency and correctness. We introduce a Self-Optimization process based on Overhead Profiling that leverages open-source LLMs to generate a high-quality dataset of correct and efficient code samples. This dataset is then used to fine-tune various LLMs. Our method involves the iterative refinement of generated code, guided by runtime performance metrics and correctness checks. Extensive experiments demonstrate that models fine-tuned on the Effi-Code show significant improvements in both code correctness and efficiency across task types. For example, the pass@1 of DeepSeek-Coder-6.7B-Instruct generated code increases from 43.3\% to 76.8\%, and the average execution time for the same correct tasks decreases by 30.5\%. Effi-Code offers a scalable and generalizable approach to improving code generation in AI systems, with potential applications in software development, algorithm design, and computational problem-solving. The source code of Effi-Code was released in https://github.com/huangd1999/Effi-Code.

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code exemplify a broader shift from passive response generation to action-oriented task execution. Yet as agents move toward open-ended, real-world deployment, relying on from-scratch reasoning and low-level tool calls for every task become increasingly inefficient, error-prone, and hard to maintain. This survey examines this challenge through the lens of agent skills, which we define as reusable procedural artifacts that coordinate tools, memory, and runtime context under task-specific constraints. Under this view, agents and skills play complementary roles: agents handle high-level reasoning and planning, while skills form the operational layer that enables reliable, reusable, and composable execution. Skills are therefore central to the scalability, robustness, and maintainability of modern agent systems. We organize the literature around four stages of the agent skill lifecycle -- representation, acquisition, retrieval, and evolution -- and review representative methods, ecosystem resources, and application settings across each stage. We conclude by discussing open challenges in quality control, interoperability, safe updating, and long-term capability management. All related resources, including research papers, open-source data, and projects, are collected for the community in blue{https://github.com/JayLZhou/Awesome-Agent-Skills}.