Multimodal Agent MemorySubmit a paper

PixelRAG

PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation

Yichuan Wang, Zhifei Li, Zirui Wang, Paul Teiletche, Lesheng Jin, Matei Zaharia, et al. · 2026-06-30

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Image
Also: text
Representation
Source- and modality-specific

How experience becomes memory

Each path is one memory component, traced from what is stored to how it is found again.

  1. screenshot tiles

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inVector-indexed collection
    3. Retrieved bySimilarity search
    4. Source evidenceSource directly available
    Pages are rendered as screenshot tiles, visually indexed, and returned directly to the reader.Full paper: Retrieval · PDF p. 9 · Figure 1

Related systems