Abstract
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.
Abstract (translated)
当前的人工智能代理能够灵活地调用工具并执行复杂任务，但它们的长期发展受到缺乏系统积累和转移技能的限制。由于没有统一的技能巩固机制，这些代理常常“重新发明轮子”，在孤立的情境中重新发现解决方案，而未能利用先前的策略。为了解决这一局限性，我们推出了SkillNet——一个旨在大规模创建、评估和组织AI技能的开放基础设施。SkillNet通过一个统一的知识体系结构来定义技能，该架构支持从不同来源创造技能，建立丰富的关联联系，并进行跨安全性、完整性、可执行性、维护性和成本意识等多维度的评价。 我们的基础设施整合了一个包含超过20万项技能的库，一个互动平台和一个多用途的Python工具包。在ALFWorld、WebShop和ScienceWorld上的实验评估表明，SkillNet显著提高了代理的表现，在多个基础模型上平均奖励增加了40%，执行步骤减少了30%。通过将技能形式化为可演化的组合资产，SkillNet为主动从短暂经验迈向持久掌握提供了坚实的基石。
URL
https://arxiv.org/abs/2603.04448
