# Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents

> 全文为英语

**Published:** 2026年10月16日
**Author:** Yujie Feng, Xiaobin Wang, Jinluan Yang, Xiaonan Shi, Pengjun Xie, Philip S. Yu, Xiaoming Wu, Jieping Ye
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/evolving-together-failing-apart-the-skill-policy-co-evolution-trap-in-se

arXiv:2610.20845v1 Announce Type: new Abstract: Skill-policy co-evolution, in which an agent's policy model and its skill bank improve each other during training, is a promising paradigm for self-improving agents. Current evaluations score the co-evolved policy on the final bank…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2610.20845)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*