Skip to content
AI News HubLIVE
Original source2 min read

RoboCoEvo: Expanding Robot Capabilities through Agent-Policy Co-Evolution

Summary

RoboCoEvo introduces a failure-guided co-evolution framework that couples the reusable executable knowledge refined by an MLLM-based agent with parameter learning in robotic foundation models such as VLA models. Using a code-as-policy formulation, the agent writes and iteratively improves failure-detection and recovery programs that yield targeted corrective experience; post-training then consolidates those behaviors into the robot's end-to-end policy, and the updated policy's failure distribution guides the next round of program revisions. Experiments on BEHAVIOR-1K, RoboCasa, and RoboTwin show sustained gains in autonomous VLA task performance across successive co-evolution rounds.

SourcearXiv RoboticsAuthor: Ran Qi, Yixin Xiao, Dawei Wang, Zhiyuan Li, Jinbang Huang, Xuan Zhao, Yintao Ma, Yangzheng Wu, Tongtong Cao, Yingxue Zhang
RoboCoEvo: Expanding Robot Capabilities through Agent-Policy Co-Evolution
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 14 Nov 2026]

Title:RoboCoEvo: Expanding Robot Capabilities through Agent-Policy Co-Evolution

View a PDF of the paper titled RoboCoEvo: Expanding Robot Capabilities through Agent-Policy Co-Evolution, by Ran Qi and 9 other authors

View PDF HTML (experimental)

Abstract:Integrating MLLM-based agents with robotic foundation models has attracted increasing attention as a means of enhancing robotic capabilities. However, the improvement of such integrated systems remains largely decoupled across their agent and model components, with advances in one component not necessarily benefiting the other, substantially limiting the capabilities of the combined system. As both MLLMs and robotic foundation models become increasingly capable, fully realizing their combined potential calls for co-evolution, an iterative process in which improvements in agents and robotic foundation models reinforce one another. We propose RoboCoEvo, a failure-guided co-evolution framework that couples the refinement of the agent's explicit and reusable executable knowledge with parameter learning in robotic foundation models, such as vision-language-action (VLA) models. Through a code-as-policy formulation, the agent develops and refines executable failure-detection and recovery programs, generating targeted corrective experience. Post-training consolidates the resulting corrective behaviors into the robotic model's end-to-end policy, improving autonomous task execution. Changes in the updated policy's failure distribution, in turn, guide subsequent revisions to the agent's programs. Experiments on BEHAVIOR-1K, RoboCasa, and RoboTwin demonstrate sustained improvements in autonomous VLA task performance across successive co-evolution rounds.

Comments: 23 pages, 8 figures, 7 tables

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.19081 [cs.RO]

(or arXiv:2611.19081v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.19081

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Dawei Wang Dr [view email] [v1] Sat, 14 Nov 2026 01:34:23 UTC (2,230 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RoboCoEvo: Expanding Robot Capabilities through Agent-Policy Co-Evolution, by Ran Qi and 9 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Proposes a failure-guided bidirectional co-evolution framework so agents and robotic foundation models reinforce each other instead of improving in isolation.
  • Uses a code-as-policy formulation in which the agent develops reusable executable failure-detection and recovery programs that generate targeted corrective experience.
  • Consolidates corrective behaviors into the VLA end-to-end policy via post-training, then uses the updated policy's failure distribution to guide the next round of agent program revisions.
  • Demonstrates sustained improvements in autonomous VLA task performance over multiple co-evolution rounds on BEHAVIOR-1K, RoboCasa, and RoboTwin.

Highlights and analysis are generated automatically and may contain errors. Check the original source.