Multimodal Agent MemorySubmit a paper

V-Mem

V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory

Dingyi Kang, Dongming Jiang, Yi Li, Guanpeng Li, Bingzhe Li · 2026-08-02

Read the paperPDF

Management
T2 Dynamic Memory
Memory changes during deployment through a stable management policy.
Primary modality
Image
Also: 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. round-organized multimodal conversation

    1. Represented asRetained perceptual source evidenceSource- and modality-specific
    2. Stored inHierarchical multi-tier store, Vector-indexed collection
    3. Retrieved bySimilarity search, Metadata / spatiotemporal retrieval
    4. Source evidenceSource directly available
    Original text and image turns are organized by conversational round and returned by target-modality routing.Full paper: Memory Construction · PDF p. 5 · Figure 1

How memory changes (T2 operations)

  • Update · Rule-based update

    During operation, V-Mem applies fixed-rule insertion or replacement to round-organized multimodal conversation; the memory state changes while the governing update policy remains fixed.

Related systems