Multimodal Agent MemorySubmit a paper

Mobile-Agent-V

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation

Junyang Wang, Haiyang Xu, Xi Zhang, Ming Yan, Ji Zhang, Fei Huang, et al. · 2025-02-24

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
GUI & computer use
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. demonstration video memory

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inFlat sequential records
    3. Retrieved byMetadata / spatiotemporal retrieval
    4. Source evidenceSource directly available
    Recorded task videos provide retained operational evidence for mobile automation.Full paper: 4.4.4 Impact of Knowledge Injection Method · PDF p. 6 · Figure 1

  2. video-derived operational knowledge

    1. Represented asPerception-to-text records & summariesCross-represented explicit
    2. Stored inHierarchical multi-tier store
    3. Retrieved byPlanner / tool-assisted retrieval
    4. Source evidenceSource linked & recoverable
    A video agent extracts operational guidance that is reused during task execution.Full-paper method / memory representation and retrieval · PDF p. 2 · Figure 1

Related systems