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.

翻译：摘要：大语言模型（LLM）智能体系统日益期望在部署后能够持续改进，但现有研究往往将两种适应目标——技能进化与多智能体系统（MAS）重构——割裂开来。这种分离可能引发组织瓶颈、上下文压力及专业化错误。我们提出SkillMAS，一种用于多智能体系统自适应专业化的无参数框架，该框架将技能进化与MAS重构相耦合。SkillMAS采用效用学习机制从已验证的执行轨迹中分配信用，通过有界技能进化在避免无筛选库增长的前提下精炼可重用流程，并在保留失败记录与执行器效用指标表明结构失配时触发基于证据的MAS重构。在具身操作、命令行执行及零售工作流等任务中，SkillMAS在既定测试框架下展现出竞争力，同时清晰阐明了部署后专业化的归因、更新与应用机制。