Abstract
Agentic robotics, centered on an Embodied System 2 formed by a foundation model and embodied harness, requires a shared evaluation framework and research roadmap to achieve reliable physical autonomy.
The release of GPT-6 Astra marks the emergence of a new paradigm in robotics: agentic robotics. Within weeks, frontier models with agentic harnesses matched or exceeded task-specific policies on many embodied benchmarks. Instead of training a dedicated policy for each family of tasks, an agentic robotic system applies a foundation model to open-world embodied tasks. It operates in a closed loop: observing the environment, interpreting user intent, reasoning about the task, invoking skills and tools, verifying outcomes, and adapting its strategy. Despite these advances, the community has yet to converge on a shared definition, a reliable evaluation framework, or a research roadmap. We argue that Embodied System 2, realized by a foundation model together with an embodied harness, forms the decision-making core of agentic robotics. Its central challenge is to translate general-purpose reasoning into effective and verifiable actions under physical constraints such as limited reaction time, mechanical limits, unpredictable environment changes, and irreversible consequences. Motivated by this perspective, we propose an evaluation framework that measures both model capabilities and closed-loop system performance. Furthermore, we identify the principles that carry over from digital to physical agents and the challenges that must be addressed to achieve reliable physical autonomy. On top of the Embodied System 2 and the evaluation framework, we envision a research roadmap toward sustained autonomy: the ability to perform work safely and reliably with progressively broader responsibility, from executing individual primitives to fulfilling standing roles.
Community
An easy-to-read blog page captures our core viewpoints. You are welcome to click:
https://grid-robotics-official.github.io/agentic-robotics-roadmap/
A shared way to evaluate this is the right ask. Benchmarks are tidy and a job site isn't. Taking a wall apart means reading what's behind it before you commit, and no two old houses match. I'd like to see the roadmap include tasks where the robot has to stop and ask because the scene isn't what the plan said.
Hi, I think this can be classified into the Safety dimension, and we have mentioned this in the Safety part.
Get this paper in your agent:
hf papers read 2611.18359 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper
