When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement

Authors: Hao Chen , Yukun Yan , Ziyu Han , Ye He , Chuanzhe Guo , Shangzhan Li , Qi Shi , Qingfu Zhu , Maosong Sun , Wanxiang Che

View a PDF of the paper titled When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement, by Hao Chen and 9 other authors

View PDF

HTML (experimental)

Abstract: Autonomous agents increasingly depend on harnesses that govern interaction, memory, tools, and execution around large language models (LLMs). While recent work has begun to evolve these harnesses from execution experience, the supervision used to guide evolution often remains relatively static, making it difficult to track changing behavioral weaknesses across rounds and potentially limiting generalization to unseen tasks. To address this issue, we propose RuHarness, a rubric--harness co-evolution framework for continual agent self-improvement. RuHarness continually discovers and reassesses behavioral criteria from execution trajectories, prioritizes the most relevant unresolved weaknesses, and uses them to guide targeted harness updates while keeping the task objective fixed. Extensive experiments across diverse agent tasks and backbone models show that RuHarness outperforms strong harness-evolution baselines, particularly on unseen held-out tasks. Further analyses show that adaptive rubric prioritization tracks shifting weaknesses and supports more sustained improvement and stable generalization across evolution rounds.

Subjects:

Artificial Intelligence (cs.AI)

Cite as:

arXiv:2610.36826 [cs.AI]

(or

arXiv:2610.36826v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.36826

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hao Chen [ view email ]

[v1]

Tue, 27 Oct 2026 08:24:44 UTC (7,265 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled When the Critic Falls Behind: Co-Evolving Rubrics and Harnesses for Continual Agent Self-Improvement, by Hao Chen and 9 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

< prev

next >

new

recent

| 2026-10

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

export BibTeX citation

Loading...

BibTeX formatted citation

loading...

Data provided by:

Bookmark

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? )