Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition Paper • 2610.28578 • Published 28 days ago • 73
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering Paper • 2610.22344 • Published Oct 15 • 28
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding Paper • 2610.19849 • Published Oct 14 • 42
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent Paper • 2606.30616 • Published Jun 29 • 104
Agents-A1 Collection Agents-A1 is a Long-horizon Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. • 12 items • Updated Jul 16 • 45
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research Paper • 2606.07591 • Published May 28 • 106
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery Paper • 2606.06473 • Published Jun 4 • 23
Sci-CoE: Co-evolving Scientific Reasoning LLMs via Geometric Consensus with Sparse Supervision Paper • 2602.12164 • Published Feb 12 • 5
P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads Paper • 2602.09443 • Published Feb 10 • 59
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery Paper • 2602.08990 • Published Feb 9 • 68
InternAgent Collection InternAgent aims to facilitate AI+X innovative research across diverse scientific domains • 14 items • Updated May 6 • 11
SWE-World: Building Software Engineering Agents in Docker-Free Environments Paper • 2602.03419 • Published Feb 3 • 42
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence Paper • 2512.22334 • Published Dec 26, 2025 • 39
SGI-Bench Collection Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows • 12 items • Updated May 6 • 37
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows Paper • 2512.16969 • Published Dec 18, 2025 • 121
Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning Paper • 2506.10521 • Published Jun 12, 2025 • 75