1
Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS
用记忆增强强化学习，让AI攻击更擅长长周期工具操纵，直指LLM多智能体系统的安全命门。
arXiv:2605.25389v1 Announce Type: cross Abstract: While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities i…