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

arXiv: https://arxiv.org/abs/2402.09727 · HTML: https://mlsanity.com/paper/2402.09727/

## Key facts

- Cited by 146 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 42 of its 52 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Placed in

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

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)

## Built on by (most cited first, 30 of 146)

- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools](https://mlsanity.com/paper/2502.04644/) (2025)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving](https://mlsanity.com/paper/2507.06229/) (2025)
- [MemInsight: Autonomous Memory Augmentation for LLM Agents](https://mlsanity.com/paper/2503.21760/) (2025)
- [CompAct: Compressing Retrieved Documents Actively for Question Answering](https://mlsanity.com/paper/2407.09014/) (2024)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models](https://mlsanity.com/paper/2406.14550/) (2024)
- [DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems](https://mlsanity.com/paper/2407.10701/) (2024)
- [On the Structural Memory of LLM Agents](https://mlsanity.com/paper/2412.15266/) (2024)
- [PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents](https://mlsanity.com/paper/2603.03296/) (2026)
- [RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code](https://mlsanity.com/paper/2503.07832/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Cognitive Memory in Large Language Models](https://mlsanity.com/paper/2504.02441/) (2025)
- [From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents](https://mlsanity.com/paper/2505.19549/) (2025)
- [DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory](https://mlsanity.com/paper/2410.08143/) (2024)
- [LongRoPE2: Near-Lossless LLM Context Window Scaling](https://mlsanity.com/paper/2502.20082/) (2025)
- [CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension](https://mlsanity.com/paper/2510.05520/) (2025)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations](https://mlsanity.com/paper/2602.19320/) (2026)
- [StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns](https://mlsanity.com/paper/2506.13356/) (2025)
- [Preference-Aware Memory Update for Long-Term LLM Agents](https://mlsanity.com/paper/2510.09720/) (2025)
- [GAM: Hierarchical Graph-based Agentic Memory for LLM Agents](https://mlsanity.com/paper/2604.12285/) (2026)
- [Geometric-Averaged Preference Optimization for Soft Preference Labels](https://mlsanity.com/paper/2409.06691/) (2024)

## 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.