# M3Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions

arXiv: https://arxiv.org/abs/2606.07402 · HTML: https://mlsanity.com/paper/2606.07402/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [MIRIX: Multi-Agent Memory System for LLM-Based Agents](https://mlsanity.com/paper/2507.07957/) (2025)
- [MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks](https://mlsanity.com/paper/2602.16313/) (2026)
- [MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation](https://mlsanity.com/paper/2211.05719/) (2022)
- [Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents](https://mlsanity.com/paper/2601.03515/) (2026)
- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [MemVerse: Multimodal Memory for Lifelong Learning Agents](https://mlsanity.com/paper/2512.03627/) (2025)
- [MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation](https://mlsanity.com/paper/2502.11903/) (2025)
- [UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities](https://mlsanity.com/paper/2504.20734/) (2025)
- [Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems](https://mlsanity.com/paper/2510.13291/) (2025)

## Built on by (most cited first, 5 of 5)

- [Mi-Memory: A Lifecycle Memory Framework for Personal AI](https://mlsanity.com/paper/2607.18975/) (2026)
- [MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off](https://mlsanity.com/paper/2608.04843/) (2026)
- [Retrieved but Not Delivered: Multimodal Memory Delivery for Long-Term Agents](https://mlsanity.com/paper/2609.32590/) (2026)
- [Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels](https://mlsanity.com/paper/2610.07984/) (2026)
- [DSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM Agents](https://mlsanity.com/paper/2610.08102/) (2026)

## Abstract (arXiv)

Language agents are increasingly deployed over accumulating multimodal information, yet existing benchmarks assume a human-human form with sparse visuals and straightforward content, evaluating neither reasoning over authentic multimodal file interaction nor the interpretation of concealed user information. We therefore introduce M3Exam, a query-centric multimodal conversational memory benchmark built on realistic user-agent interaction, with multi-dimensional evaluation spanning cross-modal grounding and implicit information inference. Benchmarking MLLMs and memory systems reveals persistent gaps in cross-modal grounding, cross session reasoning, and the efficiency cost of accumulating multimodal context. We further propose M3Proctor, a multimodal memory method that detects query modality bias and consumes raw visual sources only on demand, improving accuracy by 13% while cutting index-construction time and retrieved tokens by over 70%.