1
State Contamination in Memory-Augmented LLM Agents
揭示LLM代理因记忆摘要隐藏毒性上下文的安全漏洞，记忆污染研究新发现
arXiv:2605.16746v1 Announce Type: cross Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved contex…
揭示LLM代理因记忆摘要隐藏毒性上下文的安全漏洞，记忆污染研究新发现
arXiv:2605.16746v1 Announce Type: cross Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved contex…