SkillNet：創建、評估與連接AI技能

摘要

當前的人工智慧代理已能靈活調用工具並執行複雜任務，但其長期發展仍受制於技能缺乏系統性積累與遷移的瓶頸。由於缺少統一的技能整合機制，代理經常「重複造輪子」，在孤立情境中重新發現解決方案，卻未能有效利用既有策略。為突破此限制，我們提出SkillNet——一個專為大規模創建、評估與組織AI技能而設計的開放基礎架構。SkillNet通過統一的本體論框架構建技能體系，支持從異構來源創建技能、建立豐富的關聯關係，並實施涵蓋安全性、完整性、可執行性、可維護性與成本意識的多維度評估。我們的基礎架構整合了包含逾20萬技能的資源庫、互動式平台及多功能Python工具包。在ALFWorld、WebShop和ScienceWorld上的實驗評估表明，SkillNet能顯著提升代理性能，在多種骨幹模型上平均獎勵提升40%，執行步驟減少30%。通過將技能形式化為可演化、可組合的資產，SkillNet為代理實現從短暫經驗到持久精通的躍遷奠定了堅實基礎。

English

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.

SkillNet：創建、評估與連接AI技能

SkillNet: Create, Evaluate, and Connect AI Skills

摘要

Support