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

• URL: http://arxiv.org/abs/2604.27695v1
• Date: Thu, 30 Apr 2026 10:37:04 GMT
• Title: EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
• Abstract summary: We present EviMem, combining IRIS (Iterative Retrieval via Insufficiency Signals) and LaceMem (Layered Architecture for Conversational Evidence Memory)<n>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.
• Score: 19.027571478872
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering [42.31517185994942]
  RAG enables large language models to answer questions by accessing external knowledge.<n>Existing methods suffer from two key challenges: fragmented evidence scattered across temporally distant sessions, and noisy content within retrieved sessions that triggers the lost-in-the-middle effect.<n>We propose MemLoc, a unified Retrieve-Localize-Generate framework for long-term conversational memory QA.
  arXiv  Detail & Related papers  (2026-09-07T06:32:12Z)
• Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents [5.4775608854724345]
  Existing memory systems either compress and structure histories for efficient access or perform deep research over broader trajectories.<n>This raises a key question: can a memory system achieve strong answer quality while maintaining low online latency?<n>We introduce Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory.
  arXiv  Detail & Related papers  (2026-08-02T14:49:24Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• Eywa: Provenance-Grounded Long-Term Memory for AI Agents [0.0]
  Existing memory systems collapse source evidence, extracted facts, retrieved context, and answer policy into one opaque prompt path.<n>We present Eywa, a provenance-grounded memory architecture built around evidence before belief.
  arXiv  Detail & Related papers  (2026-05-29T02:56:35Z)
• DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA [3.56156695760535]
  Large language model (LLM) agents still struggle with long-term memory question answering.<n>We present DeferMem, a long-term memory framework that decouples this problem into high-recall candidate retrieval and query-conditioned evidence distillation.<n>On LoCoMo and LongMemEval-S, DeferMem surpasses strong baselines in QA accuracy and memory-system efficiency.
  arXiv  Detail & Related papers  (2026-05-21T12:36:46Z)
• MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models [50.25006399944962]
  Memory is essential for large vision-language models to handle long, multimodal interactions.<n>MEMLENS is a benchmark for memory in multimodal multi-session conversations.<n>We evaluate 27 LVLMs and 7 memory-augmented agents.
  arXiv  Detail & Related papers  (2026-05-14T14:41:17Z)
• MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs [47.66730296440261]
  We introduce MemQ, which propagates credit backward through a provenance DAG that records which memories were retrieved when each new memory was created.<n>Across six benchmarks, MemQ achieves the highest success rate on all six in generalization evaluation and runtime learning.<n>We further study how $$ and $$ interact with the EC-MDP structure, providing principled guidance for parameter selection and future research.
  arXiv  Detail & Related papers  (2026-05-08T18:30:24Z)
• HaS: Accelerating RAG through Homology-Aware Speculative Retrieval [9.230969223605602]
  Retrieval becomes time-consuming as the knowledge databases grow in size.<n>We propose HaS, a homology-aware speculative retrieval framework.<n>Benefiting from the prevalence of queries under real-world popularity patterns, HaS achieves substantial efficiency gains.
  arXiv  Detail & Related papers  (2026-04-22T11:15:54Z)
• MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search [59.98962867649009]
  We propose MemSearch-o1, an agentic search framework built on reasoning-aligned memory growth and retracing.<n>MemSearch-o1 grows fine-grained memory fragments from memory seed tokens from queries, then retraces and deeply refines the memory via a contribution function, and finally reorganizes a globally connected memory path.
  arXiv  Detail & Related papers  (2026-04-19T05:35:06Z)
• HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues [12.529136884264092]
  HingeMem is a boundary-guided long-term memory that builds an interpretable indexing interface via boundary-triggered hyperedges.<n> query-adaptive retrieval mechanisms jointly decide (a) textitwhat to retrieve: determine the query-conditioned routing over the element-indexed memory.<n>We show that HingeMem achieves approximately $20%$ relative improvement over strong baselines without query categories specification.
  arXiv  Detail & Related papers  (2026-04-08T09:07:07Z)
• All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution [20.68235182577703]
  All-Mem maintains a structured memory bank via explicit, non destructive consolidation.<n>Periodically offline, an LLM diagnoser proposes confidence scored topology edits executed with three operators: SPLIT, MERGE, and UPDATE.<n>At query time, typed links enable hop bounded, budgeted expansion from active anchors to archived evidence when needed.
  arXiv  Detail & Related papers  (2026-03-20T03:14:40Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval [0.0]
  SmartSearch retrieves from raw, unstructured conversation history using a fully deterministic pipeline.<n>SmartSearch achieves 93.5% on LoCoMo and 88.4% on LongMemEval-S benchmarks.
  arXiv  Detail & Related papers  (2026-03-16T17:53:21Z)
• LongVidSearch: An Agentic Benchmark for Multi-hop Evidence Retrieval Planning in Long Videos [7.139631028105273]
  LongVidSearch is a benchmark for evaluating agentic multi-hop evidence retrieval planning in long videos.<n>A Hop-k question requires exactly k necessary evidence clips, and removing any single clip renders the question unsolvable.
  arXiv  Detail & Related papers  (2026-03-15T16:20:23Z)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks [67.31276358668424]
  We introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in response to a query and link them together to generate the most informative answer.<n> AVHaystacks is an audio-visual benchmark comprising 3100 annotated QA pairs designed to assess the capabilities of LMMs in multi-video retrieval and temporal grounding task.<n>We propose a model-agnostic, multi-agent framework to address this challenge, achieving up to 89% and 65% relative improvements over baseline methods on BLEU@4 and GPT evaluation scores in QA task on our proposed AVHaystack
  arXiv  Detail & Related papers  (2025-06-08T06:34:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.