Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents
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 it trained with (the delivered bank).
By Yujie Feng, Xiaobin Wang, Jinluan Yang, Xiaonan Shi, Pengjun Xie, Philip S. Yu, Xiaoming Wu, Jieping YearXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 16, 2026.
Comments
Sign in to join the discussion.