Paper page - Which Agent’s Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams

Source: https://huggingface.co/papers/2610.27227

Abstract

GRSE improves cooperative language agents by comparing repeated executions to correctly assign behavioral credit to agent-skill pairs, outperforming prior methods on multi-hop reasoning and recovering from harmful skills.

Cooperative language-model agents can improve without weight updates by revising reusable skills, but only if a shared team reward is traced to the responsible agent and skill. Existing methods credit the skills present in each trajectory, yet presence is not responsibility: a harmful skill active in successful runs still earns positive credit. We presentGRSE,Group-Relative Skill Evolution, which assignsbehavioral creditby comparison: inspired byGRPO, it executes each question several times under the sameskill librariesand contrasts the executions to credit agent--skill pairs, with structured diagnosis of failures. On HotpotQA and LoCoMo with two open-weight actors,GRSEoutperforms MASkills, the closest prior method, on HotpotQA and every LoCoMo category except open-domain, with the largest gains on multi-hop questions (+6.7 and +3.2 F1). Its gains rest on better-grounded retrieval rather than answers given without evidence, and its learned skills transfer between the multi-hop tasks.GRSEis robust to corrupted libraries: starting from planted harmful skills, it credits every planted skill with the correct sign and recovers the score of a clean library (+6.3 points), whereas MASkills misattributes two and falls below its starting point.

View arXiv pageView PDFGitHub3Add to collection

Get this paper in your agent:

hf papers read 2610\.27227

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.27227 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.27227 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.27227 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.