Multimodal Agent MemorySubmit a paper

EvoVid

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models

Shiqi Huang, Ziyue Wang, Zhongrong Zuo, Han Qiu, Qi She, Bihan Wen · 2026-05-21

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Video & streaming
Also: text
Representation
Hybrid
Distinct operative representation paths are deliberately linked or jointly consumed by downstream reasoning, generation, or control.

How experience becomes memory

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

  1. self-evolving Video-LLM weights driven by Q-S self-play

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inFlat sequential records
    3. Retrieved byMetadata / spatiotemporal retrieval
    4. Source evidenceSource directly available
    Questioner-Solver trajectory records used as self-supervision signal. self-evolved Video-LLM is consulted at evaluation time.Full paper: Base Model (w/o training) · PDF p. 6 · Figure 1 / method overview

  2. trajectory experience

    1. Represented asSpatial, temporal & cross-modal structured memoryCross-represented explicit
    2. Stored inFlat sequential records
    3. Retrieved byMetadata / spatiotemporal retrieval
    4. Source evidenceSource not retained
    Questioner-Solver trajectory records used as self-supervision signal. self-evolved Video-LLM is consulted at evaluation time.Full paper: Algorithm and Pipeline · PDF p. 13 · Figure 1 / method overview

Related systems