# MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

arXiv: https://arxiv.org/abs/2601.21468 · HTML: https://mlsanity.com/paper/2601.21468/

## Key facts

- Cited by 15 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 39 of its 50 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

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

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.02479/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [Glyph: Scaling Context Windows via Visual-Text Compression](https://mlsanity.com/paper/2510.17800/) (2025)

## Built on by (most cited first, 15 of 15)

- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting](https://mlsanity.com/paper/2605.03804/) (2026)
- [SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation](https://mlsanity.com/paper/2608.10775/) (2026)
- [When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents](https://mlsanity.com/paper/2608.29897/) (2026)
- [POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management](https://mlsanity.com/paper/2604.14029/) (2026)
- [Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension](https://mlsanity.com/paper/2606.12898/) (2026)
- [Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression](https://mlsanity.com/paper/2608.08960/) (2026)
- [Retrieved but Not Delivered: Multimodal Memory Delivery for Long-Term Agents](https://mlsanity.com/paper/2609.32590/) (2026)
- [MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading](https://mlsanity.com/paper/2605.10268/) (2026)
- [Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text](https://mlsanity.com/paper/2606.09585/) (2026)
- [Context-Aware RL for Agentic and Multimodal LLMs](https://mlsanity.com/paper/2606.17053/) (2026)
- [MemPrism: Task-Conditioned Relational Memory Views for Long-Horizon Agents](https://mlsanity.com/paper/2608.06745/) (2026)
- [Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations](https://mlsanity.com/paper/2608.09268/) (2026)
- [MEMO: Multimodal Evidence Memory Organization for Long-Horizon LLM Agents](https://mlsanity.com/paper/2609.07471/) (2026)
- [PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins](https://mlsanity.com/paper/2609.32423/) (2026)

## Abstract (arXiv)

Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as text, where token-level cost is uniform and scales linearly with length, often spending scarce budget on low-value details. To this end, we introduce MemOCR, a multimodal memory agent that improves long-horizon reasoning under tight context budgets by allocating memory space with adaptive information density through visual layout. Concretely, MemOCR maintains a structured rich-text memory (e.g., headings, highlights) and renders it into an image that the agent consults for memory access, visually prioritizing crucial evidence while aggressively compressing auxiliary details. To ensure robustness across varying memory budgets, we train MemOCR with reinforcement learning under budget-aware objectives that expose the agent to diverse compression levels. Across long-context multi-hop and single-hop question-answering benchmarks, MemOCR outperforms strong text-based baselines and achieves more effective context utilization under extreme budgets.