EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory

Excerpt

arXiv:2604.27695v2 Announce Type: replace-cross Abstract: Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing iterative methods refine queries via generated content or document-level signals, but none explicitly diagnoses the evidence gap, namely what is missing from the accumulated retrieval set, leaving query refinement untargeted. We present EviMem, combining IRIS (Iterat