SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
For LLM-based multi-agent systems, SkillMAS addresses the decoupling of skill and structural adaptation, but results are competitive rather than state-of-the-art.
SkillMAS couples skill evolution with multi-agent system restructuring to improve post-deployment adaptation, achieving competitive performance across embodied manipulation, command-line execution, and retail workflows.
Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-agent system (MAS) restructuring. This separation can create organization bottlenecks, context pressure, and mis-specialization. We present SkillMAS, a non-parametric framework for adaptive specialization in multi-agent systems that couples skill evolution with MAS restructuring. SkillMAS uses Utility Learning to assign credit from verified execution traces, bounded skill evolution to refine reusable procedures without unfiltered library growth, and evidence-gated MAS restructuring when retained failures and Executor Utility indicate a structural mismatch. Across embodied manipulation, command-line execution, and retail workflows, SkillMAS is competitive under the reported harnesses while clarifying how post-deployment specialization is attributed, updated, and applied.