OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jinze, Zhang, Yang, Yang, Xin, Qu, Jiayi, Xu, Jinfeng, Yang, Shuo, Ding, Junhua, Ngai, Edith Cheuk-Han
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913072882384896
author Li, Jinze
Zhang, Yang
Yang, Xin
Qu, Jiayi
Xu, Jinfeng
Yang, Shuo
Ding, Junhua
Ngai, Edith Cheuk-Han
author_facet Li, Jinze
Zhang, Yang
Yang, Xin
Qu, Jiayi
Xu, Jinfeng
Yang, Shuo
Ding, Junhua
Ngai, Edith Cheuk-Han
contents Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended histories. However, existing agent memory systems are fundamentally constrained by text-context budgets: storing or revisiting raw trajectories is prohibitively token-expensive, while summarization and text-only retrieval trade token savings for information loss and fragmented evidence. To address this limitation, we propose Optical Context Retrieval Memory (OCR-Memory), a memory framework that leverages the visual modality as a high-density representation of agent experience, enabling retention of arbitrarily long histories with minimal prompt overhead at retrieval time. Specifically, OCR-Memory renders historical trajectories into images annotated with unique visual identifiers. OCR-Memory retrieves stored experience via a \emph{locate-and-transcribe} paradigm that selects relevant regions through visual anchors and retrieves the corresponding verbatim text, avoiding free-form generation and reducing hallucination. Experiments on long-horizon agent benchmarks show consistent gains under strict context limits, demonstrating that optical encoding increases effective memory capacity while preserving faithful evidence recovery.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26622
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
Li, Jinze
Zhang, Yang
Yang, Xin
Qu, Jiayi
Xu, Jinfeng
Yang, Shuo
Ding, Junhua
Ngai, Edith Cheuk-Han
Computation and Language
Autonomous LLM agents increasingly operate in long-horizon, interactive settings where success depends on reusing experience accumulated over extended histories. However, existing agent memory systems are fundamentally constrained by text-context budgets: storing or revisiting raw trajectories is prohibitively token-expensive, while summarization and text-only retrieval trade token savings for information loss and fragmented evidence. To address this limitation, we propose Optical Context Retrieval Memory (OCR-Memory), a memory framework that leverages the visual modality as a high-density representation of agent experience, enabling retention of arbitrarily long histories with minimal prompt overhead at retrieval time. Specifically, OCR-Memory renders historical trajectories into images annotated with unique visual identifiers. OCR-Memory retrieves stored experience via a \emph{locate-and-transcribe} paradigm that selects relevant regions through visual anchors and retrieves the corresponding verbatim text, avoiding free-form generation and reducing hallucination. Experiments on long-horizon agent benchmarks show consistent gains under strict context limits, demonstrating that optical encoding increases effective memory capacity while preserving faithful evidence recovery.
title OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory
topic Computation and Language
url https://arxiv.org/abs/2604.26622