Muse-Autoskill: Self-Evolving Agents via Skill Creation and Memory

Researchers have developed MUSE-Autoskill, a framework that enables large language model agents to continuously improve their task-solving abilities by creating, reusing, and refining skills through a unified lifecycle. The system introduces skill-level memory that accumulates experience across tasks, allowing agents to adapt and transfer skills more effectively. Initial tests on SkillsBench showed that lifecycle-managed skills improved task success, efficiency, reuse, and cross-agent transfer, positioning skills as long-lived, experience-aware assets rather than static artifacts.

Computer Science Artificial Intelligence Submitted on 26 May 2026 Title:MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation View PDF /pdf/2605.27366 HTML experimental https://arxiv.org/html/2605.27366v1 Abstract: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 . Our framework enables agents to create skills on demand, store and reuse them across tasks, organize and select them efficiently, and evaluate them through unit tests and runtime feedback for continuous refinement. We further introduce skill-level memory that accumulates experience for each skill across tasks, enabling more effective reuse and adaptation over time. Experiments on SkillsBench provide initial evidence that lifecycle-managed skills can improve task success, efficiency, reuse, and cross-agent transfer, highlighting the importance of treating skills as long-lived, experience-aware, and testable assets. Current browse context: cs.AI References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender 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 https://info.arxiv.org/labs/index.html .