WikiSkill：將智能體經驗彙編為持久性知識以促進技能演化

摘要

智能體技能將專業知識與工作流程封裝為可重複使用的資源，以擴展 AI 智能體的能力。近期研究從智能體的經驗中自動發掘此類技能，使智能體能透過互動逐步適應。然而，引導技能發展的洞見通常散落於最佳化歷程中，限制了它們在反覆迭代中系統性重用。我們提出 WikiSkill，一個讓智能體技能與持久性知識庫（wiki）共同演化的框架。在高層次上，WikiSkill 將原始執行經驗、累積知識與可執行技能分離，並持續將經驗整合進 wiki，而後續的技能更新可奠基於此。在各種基準測試與模型中，WikiSkill 持續優於最先進的技能演化方法，並在大多數模型-基準測試組合中優於無技能基線。我們發現技能演化與模型規模擴展互補：較大的模型通常從演化技能中受益更多，而具備技能的小型模型可以勝過規模大得多但沒有技能的模型。我們也發現演化技能在模型與模型家族之間能有效遷移，且由其他模型演化的技能可能優於自我演化的技能。最後，我們的消融研究證實，在 wiki 中持續累積知識對於技能的有效演化至關重要。這些結果展示了系統性累積與精煉智能體經驗，對於發展可重用且可遷移技能的益處。

English

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.