多智能體團隊演進時應修改哪個 Agent 的技能?GRSE 的羣組相對信用分配
Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent Teams
GRSE 透過比較同一問題的多次執行,為 Agent-技能配對分配行為責任,並診斷失敗。在 HotpotQA 和 LoCoMo 的測試中,使用兩個開放權重智能體的 GRSE 整體勝過最接近的既有方法 MASkills,多跳問題的 F1 分別提升 6.7 和 3.2。面對有害技能,GRSE 能正確判定所有預置技能的正負影響,並將乾淨技能庫的分數恢復至高 6.3 分。
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 present GRSE, Group-Relative Skill Evolution, which assigns behavioral credit by comparison: inspired by GRPO, it executes each question several times under the same skill libraries and contrasts the executions to credit agent--skill pairs, with structured diagnosis of failures. On HotpotQA and LoCoMo with two open-weight actors, GRSE outperforms 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. GRSE is 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 page View PDF GitHub Add 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 paper 0
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 paper 0
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 paper 0
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 paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co