SkillTrace Treats Agent Skill Retrieval as Graph Traversal, Hitting 53.17% on SkillsBench and 91.43% on ALFWorld

arXiv 2608.02356·medium signalXBlueskyLinkedInCopy link

As agents increasingly compose reusable skills from a library, the hard problem is not retrieving individually relevant skills but identifying a complete and executable composition. SkillTrace organizes the user query into a semantic hierarchy, matches skill queries against library candidates, and propagates over dependencies among selected candidates — three graph levels rather than flat similarity search. It reports state-of-the-art 53.17% success on SkillsBench and 91.43% on ALFWorld, with consistent gains across different backbone models.