Safety in Self-Evolving Agents: A Survey

Jiahao Chen, Zhou Feng, Oubo Ma, Yichen Yan, Ruixiao Lin, Hangtao Zhang, Linkang Du, Hengyu An, Yong Yang, Jun Liu, Junhao Li, Naen Xu, Chunyi Zhou, Yuan Su, Zehao Jin, Qianli Ma, Leyi Qi, Yiming Wang, Zhe Ma, Yuwen Pu, Mengyao Du, Yuanyi Song, Enhao Huang, Zhihui Fu, Jun Wang, Jinfeng Li, Yuefeng Chen, Hui Xue, Yiming Li, Tianyu Du, Shouling Ji

Abstract

Large language models (LLMs) exhibit strong general capabilities yet their parameters typically remain fixed after deployment, limiting learning from new interactions. In open-ended interactive environments, this characteristic motivates a shift toward self-evolving agents that continuously update reusable state (model parameters, memory entries, tool definitions, skill libraries, or workflows) using data, interactions, and accumulated experience.

This survey systematically organizes the safety and security landscape of self-evolving agents, covering threat models, attack surfaces, defense strategies, and open challenges across the self-evolution lifecycle.