paper-with-me

홈 › Papers

SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System

2026-05-10 · Shuai Pan, Yixiang Liu, Jiaye Gao, Te Gao, Weiwen Liu, Jianghao Lin, Zhihui Fu, Jun Wang, Weinan Zhang, Yong Yu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.09341

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SkillMaster: Toward Autonomous Skill Mastery in LLM Agents

2026-05-09 · Min Yang, Jinghua Piao, Xu Xia, Xiaochong Lan 외 arxiv

Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selection are typically governed by external teachers, hand-designed rule…

Skill Mastery

Agent Skill Evaluation and Evolution: Frameworks and Benchmarks

2026-06-09 · Kexin Ding, Yang Zhou, Can Jin, Feng Tong 외 arxiv

The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evaluation becomes critical to ensuring their utility, quality, and safety…

Reinforcement Learning

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

2026-08-27 · Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins 외 hf

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressi…

EvoSkill Injection: Red-Teaming Autonomous Skill Generation and Evolution in Self-Evolving Agents

2026-08-31 · Doyun Kim, Chanwoo Kim, Sugyeong Eo, Yeo-Chan Yoon 외 arxiv

LLM-based agent systems increasingly adopt skill-based architectures to reduce repetitive reasoning costs and improve stable, efficient task execution. Recent studies propose self-evolving agents that autonomously genera…

Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering

2026-05-11 · Xinyu Zhang, Zhicheng Dou, Deyang Li, Jianjun Tao 외 arxiv

As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent \textbf{Coordination Engineering}, the ability to codify and systematically improve how multiple …