Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries

TL;DR

The paper introduces GoSkills, a group-structured skill retrieval method that provides role-labeled execution contexts, improving skill relevance and agent performance over traditional flat retrieval methods.

Contribution

GoSkills offers a novel group-structured retrieval approach that enhances skill context presentation without altering downstream agent processes.

Findings

GoSkills preserves visible-requirement coverage with fewer skills.

It outperforms flat skill-access baselines in experiments.

It often improves reward and runtime efficiency.

Abstract

Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Experiments on SkillsBench and ALFWorld show that GoSkills preserves visible-requirement coverage under a small skill budget, improves over flat skill-access baselines, and often improves reward and agent-only runtime relative to structural retrieval references.