Multimodal Agent MemorySubmit a paper

STAMP

STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments

Junyang Wang, Haiyang Xu, Xi Zhang, Zhaoqing Zhu, Ming Yan, Jieping Ye, et al. · 2026-05-28

Read the paperPDF

Management
T2 Dynamic Memory
Memory changes during deployment through a stable management policy.
Primary modality
GUI & computer use
Also: Image, text
Representation
Source- and modality-specific

How experience becomes memory

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

  1. selected GUI observations

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inFlat sequential records
    3. Retrieved byPlanner / tool-assisted retrieval
    4. Source evidenceSource directly available
    Stamp-GUI learns what and when to memorize from screenshot-heavy trajectories.Full paper: Memory in GUI Agent · PDF p. 2 · Figure 1

How memory changes (T2 operations)

  • Update · Prompted LLM/VLM record update

    During operation, STAMP applies LLM-mediated memory editing to selected GUI observations; the memory state changes while the governing update policy remains fixed.

Related systems