# DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection

arXiv: https://arxiv.org/abs/2606.27499 · HTML: https://mlsanity.com/paper/2606.27499/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [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)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding](https://mlsanity.com/paper/2404.05726/) (2024)
- [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)
- [M2A: Multimodal Memory Agent with Dual-Layer Hybrid Memory for Long-Term Personalized Interactions](https://mlsanity.com/paper/2602.07624/) (2026)
- [Auto-scaling Continuous Memory for GUI Agent](https://mlsanity.com/paper/2510.09038/) (2025)
- [MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments](https://mlsanity.com/paper/2602.06075/) (2026)
- [MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory](https://mlsanity.com/paper/2605.15128/) (2026)
- [Hybrid Self-evolving Structured Memory for GUI Agents](https://mlsanity.com/paper/2603.10291/) (2026)
- [FindingDory: A Benchmark to Evaluate Memory in Embodied Agents](https://mlsanity.com/paper/2506.15635/) (2025)
- [EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents](https://mlsanity.com/paper/2601.16690/) (2026)

## Built on by (most cited first, 2 of 2)

- [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)

## Abstract (arXiv)

Agent benchmarks for measuring memory largely study textual cases, in which information is deliberately extracted from the environment, written down, and then later retrieved. In other words, they assess what agents elected to record, not what they happened to see. We introduce DMV-Bench (code: https://github.com/yyyujintang/DMV-Bench), the first interactive benchmark for visual memory in multimodal agents, to study this often-neglected property. DMV-Bench is built on (1) a controlled home-furnishing e-commerce environment, supported by a catalog of 1,000 product variants, and (2) a text-leakage contract which ensures that the primary discriminative signal of each task is solely in the pixels. In DMV-Bench, agents undergo chains of autonomous shopping sessions in which every visited product image carries a unique, pre-rendered incidental cue that the agent is later asked to recall. We show that conventional solutions struggle with this task. Inspired by dual-coding theory, we propose a memory architecture that uses parallel visual and verbal codes, which we call DualMem. On DMV-Bench, DualMem outperforms a caption-only baseline and three recent multimodal agent-memory systems across multi-session chain lengths on multiple models. These gains persist even adjusting for memory-bank size and encoding-position bias. Further experiments also reveal an asymmetric division of labor between the two codes; a weighted coding scheme is often strongest. We view this as a step towards memory systems that preserve a richer record of agents' observations.