MMUEChange: A Generalized LLM Agent Framework for Intelligent Multi-Modal Urban Environment Change Analysis

TL;DR

MMUEChange introduces a flexible multi-modal agent framework that integrates diverse urban data sources for comprehensive analysis of urban environment changes, surpassing existing methods in robustness and accuracy.

Contribution

This work presents MMUEChange, a novel modular multi-modal agent framework with a core Modality Controller for cross- and intra-modal alignment, enabling advanced urban change analysis.

Findings

Achieves 46.7% higher task success rate than baseline

Effectively reduces hallucination in multi-modal analysis

Demonstrates practical policy insights from case studies

Abstract

Understanding urban environment change is essential for sustainable development. However, current approaches, particularly remote sensing change detection, often rely on rigid, single-modal analysis. To overcome these limitations, we propose MMUEChange, a multi-modal agent framework that flexibly integrates heterogeneous urban data via a modular toolkit and a core module, Modality Controller for cross- and intra-modal alignment, enabling robust analysis of complex urban change scenarios. Case studies include: a shift toward small, community-focused parks in New York, reflecting local green space efforts; the spread of concentrated water pollution across districts in Hong Kong, pointing to coordinated water management; and a notable decline in open dumpsites in Shenzhen, with contrasting links between nighttime economic activity and waste types, indicating differing urban pressures behind domestic and construction waste. Compared to the best-performing baseline, the MMUEChange agent achieves a 46.7% improvement in task success rate and effectively mitigates hallucination, demonstrating its capacity to support complex urban change analysis tasks with real-world policy implications.