mlsanityData to 7 Oct 2026

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

arXiv 2402.09727 ↗First posted 15 Feb 2024cs.CL cs.AI cs.IRcited by 140

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Current Large Language Models (LLMs) are not only limited to some maximum context length, but also are not able to robustly consume long inputs. To address these limitations, we propose ReadAgent, an LLM agent system that increases effective context length up to 20x in our experiments. Inspired by how humans interactively read long documents, we implement ReadAgent as a simple prompting system that uses the advanced language capabilities of LLMs to (1) decide what content to store together in a memory episode, (2) compress those memory episodes into short episodic memories called gist memories, and (3) take actions to look up passages in the original text if ReadAgent needs to remind itself of relevant details to complete a task. We evaluate ReadAgent against baselines using retrieval methods, using the original long contexts, and using the gist memories. These evaluations are performed on three long-document reading comprehension tasks: QuALITY, NarrativeQA, and QMSum. ReadAgent outperforms the baselines on all three tasks while extending the effective context window by 3.5-20x.

Key facts. Cited by 140 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 42 of its 52 references that are in the map. First posted on arXiv 15 Feb 2024.

Builds on

42 of 52 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2020Longformer: The Long-Document Transformercited by 3,362
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  8. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  9. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  10. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  11. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,210
  12. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
30 more
  1. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  2. 2023PaLM 2 Technical Reportcited by 1,154
  3. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
  4. 2023Large Language Models as Optimizerscited by 830
  5. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  6. 2020Efficient Transformers: A Surveycited by 784
  7. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  8. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  9. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  10. 2023Instruction Tuning with GPT-4cited by 676
  11. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  12. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  13. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  14. 2023Language Models can Solve Computer Taskscited by 371
  15. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  16. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 350
  17. 2021Recursively Summarizing Books with Human Feedbackcited by 287
  18. 2023LongLoRA: Efficient Fine-tuning of Long-Context Large Language Modelscited by 243
  19. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  20. 2022Memorizing Transformerscited by 219
  21. 2021QuALITY: Question Answering with Long Input Texts, Yes!cited by 204
  22. 2022Re3: Generating Longer Stories With Recursive Reprompting and Revisioncited by 193
  23. 2022SCROLLS: Standardized CompaRison Over Long Language Sequencescited by 170
  24. 2023Multimodal Web Navigation with Instruction-Finetuned Foundation Modelscited by 159
  25. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 133
  26. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 129
  27. 2023System 2 Attention (is something you might need too)cited by 85
  28. 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
  29. 2023Learning to Reason and Memorize with Self-Notescited by 30
  30. 2019Interactive Machine Comprehension with Information Seeking Agentscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 46; 2026: 81.

140 papers.

Sort:

By area:

  1. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  3. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  4. 2025Survey on Evaluation of LLM-based Agentscited by 190
  5. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  6. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  7. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  8. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  9. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  10. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 90
  11. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 84
  12. 2024CompAct: Compressing Retrieved Documents Actively for Question Answeringcited by 64
38 more
  1. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 60
  2. 2024GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Modelscited by 42
  3. 2024DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systemscited by 37
  4. 2024On the Structural Memory of LLM Agentscited by 37
  5. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?cited by 30
  6. 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agentscited by 30
  7. 2025RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Codecited by 28
  8. 2025Cognitive Memory in Large Language Modelscited by 28
  9. 2024DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memorycited by 27
  10. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 27
  11. 2025CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehensioncited by 23
  12. 2025LongRoPE2: Near-Lossless LLM Context Window Scalingcited by 21
  13. 2025StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turnscited by 20
  14. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 20
  15. 2025Preference-Aware Memory Update for Long-Term LLM Agentscited by 19
  16. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 19
  17. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agentscited by 19
  18. 2024Geometric-Averaged Preference Optimization for Soft Preference Labelscited by 18
  19. 2025SpiritSight Agent: Advanced GUI Agent with One Lookcited by 18
  20. 2024Symbolic Working Memory Enhances Language Models for Complex Rule Applicationcited by 17
  21. 2025Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialoguecited by 17
  22. 2025InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformationcited by 16
  23. 2025SEDM: Scalable Self-Evolving Distributed Memory for Agentscited by 16
  24. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 16
  25. 2026APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AIcited by 16
  26. 2025Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?cited by 15
  27. 2026MemoryCD: Benchmarking Long-Context User Memory of LLM Agents for Lifelong Cross-Domain Personalizationcited by 15
  28. 2025An Empirical Study of Agent Developer Practices in AI Agent Frameworkscited by 14
  29. 2024Towards LifeSpan Cognitive Systemscited by 13
  30. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  31. 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memorycited by 12
  32. 2026Lightweight LLM Agent Memory with Small Language Modelscited by 12
  33. 2026SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activationcited by 11
  34. 2024Can't Remember Details in Long Documents? You Need Some R&Rcited by 10
  35. 2025Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Modelscited by 9
  36. 2025GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliancecited by 9
  37. 2026Belief Memory: Agent Memory Under Partial Observabilitycited by 9
  38. 2026Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agentscited by 9

50 most cited of 140 All 140 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
  2. 2026LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding
  3. 2026Coding Agents are Effective Long-Context Processors
  4. 2025Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
  5. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  6. 2024LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
  7. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
  8. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model