**摘要**
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, and none of which reliably improves over its starting point under feedback. We argue the skill should instead be trained as the external state of a frozen agent, with the same discipline that makes weight-space optimizatio
👤 作者: Yifan Yang, Ziyang Gong, Weiquan Huang, Qihao Yang, Ziwei Zhou, Zisu Huang, Yan Li, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Yuqing Yang, Dongdong Chen, Xue Yang, Chong Luo

---
🔗 **[SkillOpt ：自我发展代理技能的执行策略](https://arxiv.org/abs/2605.23904v1)**

> SkillOpt: Executive Strategy for Self-Evolving Agent Skills
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-05-26 08:00