CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation

2025-05-15

AI Summary

This paper addresses the challenge of simultaneously ensuring geographic accuracy and artistic stylization in generative AI–based cartography. We propose a multimodal large language model (MLLM)-driven multi-agent cartographic framework that emulates three sequential stages: cartographic preparation, design, and evaluation. To preserve vector-based geographic fidelity, we introduce a data–style disentanglement mechanism; to achieve stylistic rendering, we pioneer the integration of MLLMs’ visual aesthetic reasoning with domain-specific geographic knowledge—enabling automated stylesheet generation and objective quality assessment. Methodologically, we advance a multi-agent collaborative paradigm coupled with joint visual–semantic reasoning. Experiments demonstrate superior style transfer performance over baselines; human evaluations confirm high fidelity in both geographic information and aesthetic quality; and the framework exhibits scalable decision-support capabilities for professional cartography, establishing a novel GenAI-powered paradigm for expert mapmaking.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The rapid development of generative artificial intelligence (GenAI) presents new opportunities to advance the cartographic process. Previous studies have either overlooked the artistic aspects of maps or faced challenges in creating both accurate and informative maps. In this study, we propose CartoAgent, a novel multi-agent cartographic framework powered by multimodal large language models (MLLMs). This framework simulates three key stages in cartographic practice: preparation, map design, and evaluation. At each stage, different MLLMs act as agents with distinct roles to collaborate, discuss, and utilize tools for specific purposes. In particular, CartoAgent leverages MLLMs' visual aesthetic capability and world knowledge to generate maps that are both visually appealing and informative. By separating style from geographic data, it can focus on designing stylesheets without modifying the vector-based data, thereby ensuring geographic accuracy. We applied CartoAgent to a specific task centered on map restyling-namely, map style transfer and evaluation. The effectiveness of this framework was validated through extensive experiments and a human evaluation study. CartoAgent can be extended to support a variety of cartographic design decisions and inform future integrations of GenAI in cartography.

Problem

• Enhancing map style transfer with visual appeal and accuracy
• Addressing challenges in artistic and informative map creation
• Integrating multimodal LLMs for collaborative cartographic design

Innovation

• Multimodal LLM-powered multi-agent cartographic framework
• Separates style from geographic data for accuracy
• Leverages MLLMs' visual and knowledge capabilities