Multimodal Agent MemorySubmit a paper

Deep Video Discovery

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li, Bin Li, Houqiang Li, et al. · 2025-05-23

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
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. segmented clips and raw frames

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inHierarchical multi-tier store
    3. Retrieved byPlanner / tool-assisted retrieval, Metadata / spatiotemporal retrieval
    4. Source evidenceSource directly available
    The multigranular database retains clips and inspectable frames.Full-paper method / memory representation and retrieval · PDF p. 4 · Figure 1

  2. clip captions and summaries

    1. Represented asPerception-to-text records & summariesCross-represented explicit
    2. Stored inHierarchical multi-tier store, Vector-indexed collection
    3. Retrieved bySimilarity search, Planner / tool-assisted retrieval
    4. Source evidenceSource linked & recoverable
    Global and clip search use summaries, captions, embeddings, and time ranges.Full-paper method / memory representation and retrieval · PDF p. 5 · Figure 1

Related systems