# OCR-Memory: Why Text-Based Agent Memory Loses Evidence - and How Visual Encoding Fixes It

> Text memory either burns tokens or loses detail. OCR-Memory from HKU and UNT renders agent trajectories as images, retrieves verbatim evidence through visual anchors with 100% faithfulness, and cuts reasoning tokens by 6.7x - hitting 58.1% on AppWorld and 53.8% Element Accuracy on Mind2Web. Accepted at ACL 2026.

Canonical URL: https://kravhal.kcsatish.com/insights/week-17
Edition: Week 10 · May 2026
Tags: Deep Learning, LLMs, Agents, Efficiency
Reading time: 8 min read

---

This is a mirror of an article first published in the AI & Automation Chronicle.

Full text with the original formatting: https://chronicle.kcsatish.com/posts/week-17
Markdown of the original: https://chronicle.kcsatish.com/posts/week-17.md
Structured JSON of the original: https://chronicle.kcsatish.com/api/v1/posts/week-17.json

Cite the Chronicle as the publication of record for the research claims in this article.