EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 30 Apr 2026.
Builds on
16 of 29 references.
References · 16
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
- 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
- 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
- 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
- 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 400
- 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
- 2025Memory in the Age of AI Agentscited by 303
4 more
- 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 173
- 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoningcited by 38
- 2025TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialoguescited by 25
- 2022Visconde: Multi-document QA with GPT-3 and Neural Rerankingcited by 23
Built on by
Citing papers per year: 2026: 2.
2 papers.