用多模态智能体分析城市环境变化，提升决策准确性。
MMUEChange: A Generalized LLM Agent Framework for Intelligent Multi-Modal Urban Environment Change Analysis
- 构建模块化框架，通过模态控制器实现跨模态对齐
- 任务成功率比基线高46.7%，有效减少幻觉
- 适合城市规划与环境政策制定者使用
理解城市环境变化对可持续发展至关重要。当前遥感变化检测方法多依赖固定、单模态分析，难以应对复杂场景。为此，我们提出MMUEChange——一个灵活集成异构城市数据的多模态智能体框架，包含模块化工具包和核心模块“模态控制器”，实现跨模态与模态内对齐，支持复杂城市变化分析。案例包括：纽约小规模社区公园兴起，反映本地绿化努力；香港多个区域集中水污染扩散，提示需协调水管理；深圳露天垃圾场显著减少，但夜间经济活动与垃圾类型关联差异，揭示生活垃圾与建筑垃圾背后的城市压力不同。相比最优基线，MMUEChange智能体任务成功率提升46.7%，有效缓解幻觉问题，展现出在真实政策场景中支持复杂城市变化分析的能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。