AI RESEARCH
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
arXiv CS.AI
•
ArXi:2605.27366v1 Announce Type: new Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement. We propose MUSE-Autoskill Agent (Memory-Utilizing Skill Evolution), a skill-centric agent framework that lets agents continuously improve their task-solving capability by creating, reusing, and refining skills under a unified lifecycle (creation, memory, management, evaluation, and refinement