Skill Adapter: Personalized Modification and Online Routing of General-Purpose Skills
Skill Adapter is a new system that enables LLM agents to personalize and route general-purpose skills in long-horizon tasks. It distills user-specific adjustments into Adapters linked to base skills, and a routing agent selects the best skill and adapter combination based on current subtask and feedback. The system preloads candidates for future steps and uses reinforcement learning to optimize both modification and routing decisions. Evaluations on ALFWorld, WebShop, and SkillsBench show an average 11.43 percentage point improvement in task success over SkillRL and reduced execution time, with performance maintained even with a 1,000-skill pool.
This paper introduces a novel mechanism for skill personalization and online routing, showing clear gains over a strong baseline and scalability, which is valuable for advancing LLM agent autonomy.
Comments & Questions (0)
No comments yet
Be the first to comment!