{
  "id": 14582,
  "url": "https://arxiv.org/abs/2607.26643v1",
  "title": "Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting",
  "summary": "Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applications. A promising solution is to treat skills as trainable states and optimize them in the same way as model parameters in neural network training. However, data-driven skill optimization is prone to overfitting to the limited trajectories collected from real environments. Overexploiting these trajectories overfits the current batch, while unconst",
  "authors": "Hongqiang Lin, Chao Liu, Xiaofan Bai, Xuan Jin, Yuhong Li, Nenggan Zheng et al.",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-29T09:05:40.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/14582",
  "original_url": "https://arxiv.org/abs/2607.26643v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}