MUSE-Autoskill: 通过技能创建、记忆、管理和评估实现自我进化智能体
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
AI总结：
提出MUSE-Autoskill框架，通过统一的技能生命周期（创建、记忆、管理、评估和优化）使LLM智能体持续提升任务解决能力，实验表明生命周期管理的技能可提高任务成功率、效率、复用性和跨智能体迁移。
摘要：
大型语言模型（LLM）智能体依赖可复用技能来解决复杂任务。然而，现有的技能创建方法将技能视为孤立和静态的工件，限制了其可复用性、可靠性和长期改进。我们提出了MUSE-Autoskill智能体（记忆利用技能进化），一个以技能为中心的智能体框架，让智能体通过统一的技能生命周期（创建、记忆、管理、评估和优化）持续提升任务解决能力。我们的框架使智能体能够按需创建技能，跨任务存储和复用技能，高效组织和选择技能，并通过单元测试和运行时反馈评估技能以进行持续优化。我们进一步引入了技能级记忆，为每个技能跨任务积累经验，从而实现更有效的复用和随时间适应。在SkillsBench上的实验提供了初步证据，表明生命周期管理的技能可以提高任务成功率、效率、复用性和跨智能体迁移，突出了将技能视为长期存在、具有经验意识和可测试资产的重要性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
