Collaborative Memory for Multi-Agent VLM Systems

2026-09-15

AI Summary

本文针对多智能体视觉-语言模型系统中的共享视觉上下文问题，通过构建记忆层次、跨智能体共享及一致性机制来解决。

Abstract

Vision-language model (VLM) agents combine specialized perception, tools, and reasoning to address complex visual tasks. In multi-agent settings, different agents inspect different image regions, video frames, or visual representations, so collaboration extends beyond distributed reasoning to distributed perception. This makes shared visual context a central problem in VLM agent collaboration. In this paper, we frame memory hierarchy, cross-agent sharing, and consistency mechanisms around the need to reconcile interpretations and update dependent reasoning. Effective collaboration requires agents to build on contributions from other agents, recover missing visual context, and reconcile differing interpretations as new evidence emerges. Shared visual memory preserves not only images or textual summaries but also the dependencies among observations, agent interpretations, and subsequent reasoning. Together, these design considerations shape how information flows and evolves across VLM agents. The proposed framework provides a foundation for building reliable and resource-efficient agent teams.

Problem

• multi-agent VLM
• shared visual context
• collaboration
• memory hierarchy
• cross-agent sharing

Innovation

• Collaborative Memory
• Multi-Agent VLM Systems
• Shared Visual Context
• Cross-Agent Sharing
• Consistency Mechanisms