One Skill, Many Websites: Learning Generalizable Skills Through Polymorphic Abstraction

ICLR 2026 Conference Submission21560 Authors

Keywords: Skill Induction, Agent, Polymorphism, Continual Learning, Large Language Models

TL;DR: We proposed PolySkill, a framework that guides Web Agents to induce skills that is generalized and transfer better across different websites, unlike existing methods that produce over-specialized, non-transferable skills.

Abstract:

Large language models (LLMs) are moving beyond static uses and are now powering agents that learn 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 \ours enhance the agent 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.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 21560