AI 译本 · Equalang
新上架PDF · 2026年11月翻译 · 公式优化
加载中…
加载中…
arXiv · 2026
WikiSkill：将智能体经验编纂为持久知识，推动技能演进
Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins et al.
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 progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, our ablation studies confirm that persistent knowledge accumulation in the wiki is critical for effective skill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.
智能体技能将专业知识和工作流封装为可重复使用的资源，从而扩展 AI 智能体的能力。近期研究开始从智能体的经验中自动发现这类技能，使智能体能够通过交互逐步适应。然而，指导技能开发的见解通常散落在优化过程的历史记录中，限制了它们在多轮迭代中的系统性复用。我们提出 WikiSkill，这是一种使智能体技能与持久知识库（wiki）协同演进的框架。总体而言，WikiSkill 将原始执行经验、积累的知识和可执行技能区分开来，同时持续将经验整合到 wiki 中，供后续技能更新借鉴。在多种基准和模型上，WikiSkill 的表现始终优于最先进的技能演进方法，并在大多数模型与基准的组合设置中优于不使用技能的基线。我们发现，技能演进能够补充模型扩展：较大的模型通常能从演进后的技能中获益更多，而配备技能的较小模型，其表现可以大幅超过未配备技能的大得多的模型。我们还发现，演进后的技能能够有效迁移到不同模型及模型系列中，而且由其他模型演进出的技能可能优于模型自行演进出的技能。最后，我们的消融研究证实，wiki 中持久积累知识对于有效的技能演进至关重要。这些结果表明，系统地积累和提炼智能体经验，有助于开发可重复使用、可迁移的技能。
PDF · 2026年11月翻译 · 公式优化