Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
arXiv:2610.13267v1 Announce Type: new Abstract: Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either static memory isolation or continuous online auditing, resulting in low memory efficiency and high computational overhead. To address these limitations, inspired by neuroscientific mechanisms that weak reactivation can destabilize memories and induce decay in the absence of reinforcement, we propose a…