EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
cs.CV, cs.CL
Submitted: 2026-04-30
Updated: 2026-09-08
Code: https://github.com/AIGeeksGroup/EviMem
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions.
Terminology
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 (Iterative Retrieval via Insufficiency Signals), a closed-loop framework that detects evidence gaps through sufficiency evaluation, diagnoses what is missing, and drives targeted query refinement, with LaceMem (Layered Architecture for Conversational Evidence Memory), a coarse-to-fine memory hierarchy supporting fine-grained gap diagnosis. On LoCoMo, EviMem improves Judge Accuracy over MIRIX on temporal (73.3% to 81.6%) and multi-hop (65.9% to 85.2%) questions at 4.5x lower latency. Code: https://github.com/AIGeeksGroup/EviMem.
Sources
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Memory in the Age of AI Agents
- LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
- MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
- Evaluating Very Long-Term Conversational Memory of LLM Agents
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- MemGPT: Towards LLMs as Operating Systems
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
- MIRIX: Multi-Agent Memory System for LLM-Based Agents
- A-MEM: Agentic Memory for LLM Agents
- Corrective Retrieval Augmented Generation
- BERTScore: Evaluating Text Generation with BERT
- MemoryBank: Enhancing Large Language Models with Long-Term Memory
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models