RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution

Abstract

LLM-based agents are increasingly deployed in product-level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater risks than unsafe text generation alone. Existing automatic red-teaming methods often rely on fixed attacks, while recent agentic attackers coordinate multiple jailbreak tools and show stronger potential through trajectory-based retrieval. However, such retrieval can reuse misleading experiences due to retrieval bias and unc

Categories

Framework mappings

Suggested from the entry's categories.

@misc{zhang2026redevoagent,
  title = {{RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution}},
  author = {Junjie Zhang and Hui Liu and Kecheng Chen and Xianbo Mo and Changsheng Chen and Haoliang Li},
  year = {2026},
  month = aug,
  eprint = {2608.27439},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.27439}
}