{"ID":2921782,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T05:56:00.181519634Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01311","arxiv_id":"2606.01311","title":"SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories","abstract":"Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill adaptation pipelines usually update skills from full trajectories or session-level feedback, which makes failure attribution coarse and often produces unstable or overly broad revisions. We propose SkillAdaptor, a training-free step-level skill adaptation framework with explicit failure attribution, and it can plug into OpenClaw-class agent harnesses. Given a failed trajectory, SkillAdaptor identifies a first actionable fault step, links responsibility to candidate skills, and applies targeted updates under explicit acceptance checks while keeping the backbone frozen. We evaluate on WebShop, PinchBench, and Claw-Eval with Kimi-K2.5, GLM-5, and GPT-5.2. SkillAdaptor improves over no-skill and skill-adaptation baselines on all three suites, with the largest single-metric improvements of +1.5 points on PinchBench Avg Score%, +1.8 on Claw-Eval Avg Score, and +1.7 on WebShop success rate. These results indicate that step-level attribution supports more stable and auditable training-free skill maintenance\\footnote{The code will be released at https://github.com/zjunlp/SkillAdaptor.}.","short_abstract":"Large language model (LLM) agents increasingly rely on reusable external skills to solve long-horizon interactive tasks. Existing training-free skill adaptation pipelines usually update skills from full trajectories or session-level feedback, which makes failure attribution coarse and often produces unstable or overly...","url_abs":"https://arxiv.org/abs/2606.01311","url_pdf":"https://arxiv.org/pdf/2606.01311v1","authors":"[\"Zhuoyun Yu\",\"Xin Xie\",\"Wuguannan Yao\",\"Chenxi Wang\",\"Lei Liang\",\"Xiang Qi\",\"Shumin Deng\"]","published":"2026-05-31T16:00:10Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":612604,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T02:42:49.606572591Z","DeletedAt":null,"paper_id":2921782,"paper_url":"https://arxiv.org/abs/2606.01311","paper_title":"SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories","repo_url":"https://github.com/zjunlp/SkillAdaptor","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}