aiqbench analysis
This research introduces SkillMorph, a method that uses trajectory-guided fault localization to automatically refine agent skills by linking execution evidence to specific behavioral contents. By comparing failure and success trajectories across repeated runs, the approach identifies suspicious actions to generate precise revisions without relying solely on manual refinement or ungrounded LLM guesses. The technique demonstrates improved trial-level accuracy and execution consistency in code agents, marking a significant step toward more reliable autonomous software development workflows.
Trajectory-Guided Fault Localization for Agent Skill Evolution
arXiv:2610.11858v1 Announce Type: cross Abstract: Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement, recent approaches use LLMs to generate revisions from execution feedback. However, grounding these revisions in explicit behavioral evidence remains challenging. To address this gap, we propose SkillMorph, a skill-evolution approach based on trajectory-guided fault localization in agent skills. Its core idea is to link execution evidence to specific skill contents before generating revisions. Specifically, SkillMorph compares failure and success evidence in abstracted trajectories across repeated runs and tasks, incorporating changes between evolution loops to identify suspicious actions. It then uses these suspicious actions to localize edit sites in the skills and generate corresponding revisions. Experiments on SWE-Skills-Bench and CannBot show that the skills evolved by SkillMorph consistently achieve higher trial-level accuracy and execution consistency than the original skills and those from four existing skill-evolution methods. We have also applied SkillMorph to automated kernel generation with an AI operator-development team, which has accepted 6 skill-revision pull requests.
Abstract:Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort of skill refinement, recent approaches use LLMs to generate revisions from execution feedback. However, grounding these revisions in explicit behavioral evidence remains challenging. To address this gap, we propose SkillMorph, a skill-evolution approach based on trajectory-guided fault localization in agent skills. Its core idea is to link execution evidence to specific skill contents before generating revisions. Specifically, SkillMorph compares failure and success evidence in abstracted trajectories across repeated runs and tasks, incorporating changes between evolution loops to identify suspicious actions. It then uses these suspicious actions to localize edit sites in the skills and generate corresponding revisions. Experiments on SWE-Skills-Bench and CannBot show that the skills evolved by SkillMorph consistently achieve higher trial-level accuracy and execution consistency than the original skills and those from four existing skill-evolution methods. We have also applied SkillMorph to automated kernel generation with an AI operator-development team, which has accepted 6 skill-revision pull requests.
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
arXiv:2610.11858 [cs.SE]
(or arXiv:2610.11858v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2610.11858 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 268 words
Related coverage
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
arXiv · Oct 1, 2026
A Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents
arXiv · Sep 25, 2026
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
arXiv · Jun 17, 2026
SkillEvoLean: Mutation-enhanced skill evolution for Lean provers
arXiv · Oct 2, 2026