Multimodal Agent MemorySubmit a paper

MMA

MMA: Multimodal Memory Agent

Yihao Lu, Wanru Cheng, Zeyu Zhang, Hao Tang · 2026-02-18

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Image
Also: text
Representation
Hybrid
Distinct operative representation paths are explicitly linked for downstream retrieval, reasoning, or control.

How experience becomes memory

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

  1. multimodal evidence items

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inVector-indexed collection
    3. Retrieved bySimilarity search
    4. Source evidenceSource directly available
    Retrieved visual and textual evidence remains available for grounded answering.Full paper: Memory-Augmented LLM Agents. Memory- · PDF p. 2 · Figure 1

  2. reliability and conflict network

    1. Represented asSpatial, temporal & cross-modal structured memoryCross-represented explicit
    2. Stored inGraph / relational store
    3. Retrieved byStructure traversal
    4. Source evidenceSource linked & recoverable
    Memory items receive source-credibility, temporal-decay, and conflict-consensus signals that remain linked to the evidence.Full paper: Multimodal Memory Agent (MMA) · PDF p. 3 · Figure 1

Related systems