MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models

Excerpt

arXiv:2605.28009v2 Announce Type: replace-cross Abstract: Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral rules into a shared space, allowing functionally distinct memories to be retrieved and used as interchangeable evidence. We identify this failure mode as heterogeneous memory contamination, where context-