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

arXiv: https://arxiv.org/abs/2601.05483 · HTML: https://mlsanity.com/paper/2601.05483/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models](https://mlsanity.com/paper/2406.08487/) (2024)
- [Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models](https://mlsanity.com/paper/2401.09083/) (2024)
- [Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images](https://mlsanity.com/paper/2009.12596/) (2020)
- [Few-shot Object Detection with Feature Attention Highlight Module in Remote Sensing Images](https://mlsanity.com/paper/2009.01616/) (2020)
- [LLM Agent Framework for Intelligent Change Analysis in Urban Environment using Remote Sensing Imagery](https://mlsanity.com/paper/2601.02757/) (2026)

## Built on by (most cited first, 1 of 1)

- [Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework](https://mlsanity.com/paper/2606.12065/) (2026)

## Abstract (arXiv)

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.