{
  "id": 4557,
  "url": "https://arxiv.org/abs/2605.10500v1",
  "title": "SkillEvolver: Skill Learning as a Meta-Skill",
  "summary": "Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \\textbf{SkillEvolver}, a lightweight, plug-and-play solution for online skill learning, in which a single meta-skill iteratively authors, deploys, and refines domain-specific skills. The learning target of SkillEvolver is the skill's prose and code, not model weights, so that the resultin",
  "authors": "Genrui Zhang, Erle Zhu, Jinfeng Zhou, Caiyan Jia, Hongning Wang",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": "meta",
  "regions": null,
  "published_at": "2026-05-11T12:58:25.000Z",
  "fetched_at": "2026-07-14T16:31:03.581Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4557",
  "original_url": "https://arxiv.org/abs/2605.10500v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}