1
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
揭示记忆增强的LLM代理在长期使用中面临的安全风险，提醒关注AI系统持续记忆带来的新威胁。
arXiv:2605.17830v1 Announce Type: cross Abstract: Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an ag…