PolySkill: 通过多态抽象学习通用技能
PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction
AI总结：
PolySkill通过多态抽象方法使智能体能学习通用且可组合的技能，提升技能重用性和成功率，减少步骤并增强自我探索能力。
摘要：
大型语言模型（LLMs）正超越静态用途，现在正在驱动能够在其与外部环境交互过程中持续学习的智能体。例如，智能体可以在浏览网页或切换新工具时学习可重用的技能。然而，现有的技能学习方法往往生成过于专门化于单一网站的技能，无法泛化。我们引入了PolySkill，一种新的框架，使智能体能够学习通用且可组合的技能。核心思想受软件工程中的多态启发，是将技能的抽象目标（它完成什么）与其具体实现（如何执行）解耦。实验显示，我们的方法（1）在已见网站上提高了技能重用性1.7倍；（2）在Mind2Web上将成功率提高了9.4%，在未见网站上提高了13.9%，同时减少了20%以上的步骤；（3）在无指定任务的自我探索设置中，我们的框架提高了所提议任务的质量，并使智能体能够学习在不同网站上有效工作的通用技能。通过使智能体能够识别和优化其自身目标，PolySkill增强了智能体学习更好课程的能力，从而获得比基线方法更通用的技能。这项工作为构建能够持续学习于适应性环境中的智能体提供了实用路径。我们的发现表明，将技能的目标与其执行分离是向开发能够持续学习和泛化于开放网络的自主智能体的关键一步。我们的代码可在https://github.com/simonucl/PolySkill中找到。
英文摘要：
Large language models (LLMs) are moving beyond static uses and are now powering agents that learn continually during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or toggling new tools. However, existing methods for skill learning often create skills that are over-specialized to a single website and fail to generalize. We introduce PolySkill, a new framework that enables agents to learn generalizable and compositional skills. The core idea, inspired by polymorphism in software engineering, is to decouple a skill's abstract goal (what it accomplishes) and its concrete implementation (how it is executed). Experiments show that our method (1) improves skill reuse by 1.7x on seen websites and (2) boosts success rates by up to 9.4% on Mind2Web and 13.9% on unseen websites, while reducing steps by over 20%. (3) In self-exploration settings without specified tasks, our framework improves the quality of proposed tasks and enables agents to learn generalizable skills that work across different sites. By enabling the agent to identify and refine its own goals, the PolySkill enhances the agent's ability to learn a better curriculum, leading to the acquisition of more generalizable skills compared to baseline methods. This work provides a practical path toward building agents capable of continual learning in adaptive environments. Our findings show that separating a skill's goal from its execution is a crucial step toward developing autonomous agents that can learn and generalize across the open web continuously. Our code can be found in https://github.com/simonucl/PolySkill.
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。
