自主進化智能體技能管理

Computer Science > Artificial Intelligence arXiv:2605.27366 (cs) [Submitted on 26 May 2026 (v1), last revised 3 Jul 2026 (this version, v2)] Title:MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation Authors:Huawei Lin, Peng Li, Jie Song, Fuxin Jiang, Tieying Zhang View a PDF of the paper titled MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation, by Huawei Lin and 4 other authors View PDF HTML (experimental) Abstract:Large language model (LLM) agents rely on reusable skills to solve complex tasks, but existing skill creation approaches often treat skills as isolated, static artifacts, limiting reusability, reliability, and long-term improvement. We propose MUSE-Autoskill Agent (Memory-Utilizing Skill Evolution), a skill-centric agent framework that creates, reuses, and refines skills under a unified lifecycle: creation, memory, management, evaluation, and refinement. MUSE creates skills on demand, stores them across tasks, retrieves them through a skill catalog, and accumulates per-skill experience for later reuse and adaptation. Across the main reported settings on SkillsBench and SkillLearnBench, MUSE-Autoskill outperforms Hermes, Codex, and Claude Code. On SkillsBench, its self-created skills surpass human-authored skills on the successfully covered subset (85.24% vs. 81.17%), showing that lifecycle-managed skills can distill agent experience into highly effective reusable assets; MUSE-created skills also transfer to Hermes more effectively than Codex- or Claude-created skills, reaching 51.90% accuracy under transfer. These results highlight the importance of treating skills as long-lived, experience-aware, and testable assets. Comments: 30 pages, 9 figures, 15 tables, Under Review Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Multiagent Systems (cs.MA) Cite as: arXiv:2605.27366 [cs.AI] (or arXiv:2605.27366v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2605.27366 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Huawei Lin [view email] [v1] Tue, 26 May 2026 17:59:19 UTC (1,113 KB) [v2] Fri, 3 Jul 2026 08:22:38 UTC (1,393 KB) Full-text links: Access Paper: View a PDF of the paper titled MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation, by Huawei Lin and 4 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-05 Change to browse by: cs cs.CL cs.LG cs.MA References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)