Multimodal Agent MemorySubmit a paper

ScriptViz

The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

Chenyu Mu, Xin He, Qu Yang, Wanshun Chen, Jiadi Yao, Huang Liu, et al. · 2026-05-27

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Video & streaming
Also: text, Image, GUI & computer use
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. Last/first-frame visual anchor carried to the next scene

    1. Represented asPerception-to-text records & summariesCross-represented explicit
    2. Stored inHierarchical multi-tier store
    3. Retrieved byPlanner / tool-assisted retrieval
    4. Source evidenceSource not retained
    Anchor frame (image) extracted per scene. The anchor frame is passed as conditioning to the next scene, with a 'continuing from the previous scene' text cue.Full-paper method / memory representation and retrieval · PDF p. 6 · Figure 1 / method overview

Related systems