Multimodal Agent MemorySubmit a paper

MAP-VLA

MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation

Runhao Li, Wenkai Guo, Zhenyu Wu, Changyuan Wang, Haoyuan Deng, Zhenyu Weng, et al. · 2025-11-12

Read the paperPDF

Management
T1 Static Memory
Memory is built once and reused without change during deployment.
Primary modality
Embodied & 3D
Also: Image, text
Representation
Internalized latent & parametric

How experience becomes memory

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

  1. stage-specific soft prompts

    1. Represented asExperience-conditioned parametric memoryInternalized latent & parametric
    2. Stored inModular adapter bank
    3. Retrieved bySimilarity search, Latent / parametric activation
    4. Source evidenceSource not retained
    Historical demonstrations become stage prompts retrieved by trajectory similarity.Full paper: C. Memory-Augmented Action Generation · PDF p. 4 · Figure 1

Related systems