GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural Networks

TL;DR

GraphGeo introduces a multi-agent debate framework utilizing heterogeneous graph neural networks to improve visual geo-localization accuracy by modeling diverse relationships and conflict resolution among agents.

Contribution

The paper presents a novel debate-based multi-agent framework with typed edges and dual-level reasoning, advancing the state-of-the-art in visual geo-localization.

Findings

Significantly outperforms existing methods on multiple benchmarks.

Effectively models complex debate relationships with heterogeneous graphs.

Enhances geo-localization accuracy through structured agent debate.

Abstract

Visual geo-localization requires extensive geographic knowledge and sophisticated reasoning to determine image locations without GPS metadata. Traditional retrieval methods are constrained by database coverage and quality. Recent Large Vision-Language Models (LVLMs) enable direct location reasoning from image content, yet individual models struggle with diverse geographic regions and complex scenes. Existing multi-agent systems improve performance through model collaboration but treat all agent interactions uniformly. They lack mechanisms to handle conflicting predictions effectively. We propose \textbf{GraphGeo}, a multi-agent debate framework using heterogeneous graph neural networks for visual geo-localization. Our approach models diverse debate relationships through typed edges, distinguishing supportive collaboration, competitive argumentation, and knowledge transfer. We introduce a dual-level debate mechanism combining node-level refinement and edge-level argumentation modeling. A cross-level topology refinement strategy enables co-evolution between graph structure and agent representations. Experiments on multiple benchmarks demonstrate GraphGeo significantly outperforms state-of-the-art methods. Our framework transforms cognitive conflicts between agents into enhanced geo-localization accuracy through structured debate.