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

arXiv:2610.27227v1 Announce Type: new Abstract: 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 extbf{GRSE}, extbf{G}roup-extbf{R}elative extbf{S}kill extbf{E}volution, 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.

Related

• SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization
• SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
• Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
• Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems

Source: arXiv cs.CL | 2026-10-21