AI RESEARCH

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

arXiv CS.CL

ArXi:2604.26622v1 Announce Type: new 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.