Preprint
Aug 2026
RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
RedEvoAgent is proposed, a black-box red-teaming agent that distills cross-case attack trajectories into a concise, human-readable attack skill that outperforms fixed and agentic baselines, improves tool efficiency, and transfers across attacker models and target execution harnesses.
Jun-Jie Zhang, Hui Liu, Ke-Cheng Chen et al.
· 0 citations