Back to AI News
arxiv

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.

AI Brief

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.

arXiv:2611.17007v1 Announce Type: new Abstract: Large language model (LLM) agents use external skills to reuse task procedures and experience with tools. General-purpose skills describe shared execution procedures, while specific tool choices, operating practices, and output requirements vary across users. In long-horizon tasks, subgoals, available inputs, and environmental states change as execution progresses. Agents must select currently applicable skills from an expanding skill pool and prepare candidates for subsequent steps. We propose Skill Adapter, which enables personalized modification and online routing of general-purpose skills. The system distills local adjustments from user requirements and execution feedback and stores them as Adapters linked to general-purpose skills. The routing agent selects general-purpose skills and applicable Adapters based on the current subtask, execution progress, and environmental feedback, incrementally maintaining a task-level online skill library that the main LLM reads on demand. The system preloads candidates for subsequent nodes and rechecks their applicability once actual inputs are determined. Reinforcement learning optimizes the two types of decisions using modification gains and routing outcomes, respectively. We evaluate Skill Adapter on ALFWorld, WebShop, and SkillsBench. Compared with SkillRL, it improves task success rates by an average of 11.43 percentage points and reduces mean execution time on all three benchmarks. Skill Adapter retains its performance advantage when the skill pool grows to 1,000 skills.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!