A Survey on the Security of Long-Term Memory in LLM Agents: Toward Mnemonic Sovereignty

Zehao Lin, Chunyu Li, Kai Chen

Abstract

Research on large language model (LLM) security is shifting from "will the model leak training data" to a more consequential question: can an agent with persistent, long-term memory be continuously shaped, cross-session poisoned, accessed without authorization, and propagated across shared organizational state? Recent surveys cover memory architectures and agent mechanisms, but fewer center the epistemic and governance properties of persistent, writable memory as the reason memory is an independ

Categories

Cite This Resource

@article{llmsec202600143,
  title = {A Survey on the Security of Long-Term Memory in LLM Agents: Toward Mnemonic Sovereignty},
  author = {Zehao Lin and Chunyu Li and Kai Chen},
  year = {2026},
  url = {https://arxiv.org/abs/2604.16548},
}