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

2024-02-15 · Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John Canny, Ian Fischer

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.

📄 PDF Abstract BibTeX arXiv:2402.09727

Code (0)

등록된 구현이 없습니다.

Tasks

Reading Comprehension Retrieval

HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents

2026-04-18 · Jinchang Zhu, Jindong Li, Cheng Zhang, Jiahong Liu 외 arxiv

Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstruc…

Semantic Similarity

Reading Like HER: Human Reading Inspired Extractive Summarization

2019-11-01 · IJCNLP 2019 11 · Ling Luo, Xiang Ao, Yan Song, Feiyang Pan 외

In this work, we re-examine the problem of extractive text summarization for long documents. We observe that the process of extracting summarization of human can be divided into two stages: 1) a rough reading stage to lo…

Decision Making Extractive Summarization Extractive Text Summarization Text Summarization

SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation

2026-01-06 · Hanqi Jiang, Junhao Chen, Yi Pan, Ling Chen 외 arxiv

While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory. To bridge this gap, we introduce Synapse (Sy…

CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

2025-10-07 · Rui Li, Zeyu Zhang, Xiaohe Bo, Zihang Tian 외 arxiv

Current Large Language Models (LLMs) are confronted with overwhelming information volume when comprehending long-form documents. This challenge raises the imperative of a cohesive memory module, which can elevate vanilla…

Reading Comprehension Question Answering

Human-Like Lifelong Memory: A Neuroscience-Grounded Architecture for Infinite Interaction

2026-03-30 · Diego C. Lerma-Torres arxiv

Large language models lack persistent, structured memory for long-term interaction and context-sensitive retrieval. Expanding context windows does not solve this: recent evidence shows that context length alone degrades …