Multimodal Agent MemorySubmit a paper

Vgent

Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding

Xiaoqian Shen, Wenxuan Zhang, Jun Chen, Mohamed Elhoseiny · 2025-10-15

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Video & streaming
Also: Image, text
Representation
Cross-represented explicit

How experience becomes memory

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

  1. clip descriptions linked by shared entities

    1. Represented asSpatial, temporal & cross-modal structured memoryCross-represented explicit
    2. Stored inGraph / relational store
    3. Retrieved byStructure traversal, Planner / tool-assisted retrieval
    4. Source evidenceSource linked & recoverable
    A clip graph preserves temporal and entity relations for retrieval and verification.Full paper: Graph-based Retrieval · PDF p. 5 · Figure 1

Related systems