[论文解读] Towards Intelligent Urban Park Development Monitoring: LLM Agents for Multi-Modal Information Fusion and Analysis

Zixuan Xiao, Chunguang Hu+1 more|arXiv (Cornell University)|Jan 28, 2026

Remote-Sensing Image Classification被引用 0

一句话总结

本文提出一个面向城市公园开发监测的多模态大模型代理框架，能够在异质数据源之间进行鲁棒的数据融合与分析，并通过领域专用工具包降低幻觉现象。

ABSTRACT

As an important part of urbanization, the development monitoring of newly constructed parks is of great significance for evaluating the effect of urban planning and optimizing resource allocation. However, traditional change detection methods based on remote sensing imagery have obvious limitations in high-level and intelligent analysis, and thus are difficult to meet the requirements of current urban planning and management. In face of the growing demand for complex multi-modal data analysis in urban park development monitoring, these methods often fail to provide flexible analysis capabilities for diverse application scenarios. This study proposes a multi-modal LLM agent framework, which aims to make full use of the semantic understanding and reasoning capabilities of LLM to meet the challenges in urban park development monitoring. In this framework, a general horizontal and vertical data alignment mechanism is designed to ensure the consistency and effective tracking of multi-modal data. At the same time, a specific toolkit is constructed to alleviate the hallucination issues of LLM due to the lack of domain-specific knowledge. Compared to vanilla GPT-4o and other agents, our approach enables robust multi-modal information fusion and analysis, offering reliable and scalable solutions tailored to the diverse and evolving demands of urban park development monitoring.

研究动机与目标

• 促使对新建城市公园的监测改进，以支持城市规划与资源分配。
• 解决传统遥感变化检测在提供高层次、智能分析方面的局限性。
• 实现适用于多样化、不断演化的城市公园开发场景的灵活多模态数据分析。
• 开发数据对齐机制，确保异质数据源的一致性。

提出的方法

• 提出一个面向多模态数据对齐的通用水平与垂直数据对齐机制。
• 构建面向领域的工具包，以缓解LLM幻觉并弥补知识空缺。
• 部署并将所提的LLM代理框架与原生GPT-4o及其他代理进行对比，以评估在多模态融合与分析中的鲁棒性。

实验结果

研究问题

• RQ1 如何对多模态数据进行对齐，以实现跨来源对城市公园开发的一致分析？
• RQ2 领域专用的工具包是否能够减少LLM幻觉并提高城市公园监测任务的可靠性？
• RQ3 所提出的LLM代理框架在与基线代理相比的多模态信息融合鲁棒性方面表现如何？
• RQ4 在不断演化的城市公园开发场景中应用LLM代理的挑战与收益是什么？

主要发现

• 该框架支持用于城市公园监测的鲁棒多模态信息融合与分析。
• 设计了水平与垂直的数据对齐机制，以确保一致性和有效的数据跟踪。
• 构建了面向领域的工具包，以缓解由于知识空缺引起的LLM幻觉。
• 所提出的方法在跨模态融合与分析的鲁棒性方面优于原生GPT-4o与其他代理。