GeoCivic-Agent: A Multimodal Agentic GeoAI Framework for Spatial Understanding and Decision Support of Public Participation Data in Smart Cities
DOI:
https://doi.org/10.66238/fsrma142Keywords:
GeoAI, Multimodal Learning, Large Language Model, Vision-Language Model, Multi-Agent System, Spatial Intelligence, Public Participation, Smart City, Urban ComputingAbstract
The rapid development of smart cities has increased the demand for intelligent and participatory urban governance, where public opinions provide valuable insights into transportation safety, environmental quality, housing conditions, and public service deficiencies. However, massive civic feedback collected from online platforms, social media, and mobile applications is often presented as heterogeneous and unstructured data, including texts, images, and geographic information, which limits the ability of existing urban analysis systems to discover spatial patterns and support planning decisions. This study proposes GeoCivic-Agent (Multimodal Agentic Geographic Artificial Intelligence Framework for Spatial Understanding and Decision Support of Public Participation Data), a novel framework that integrates Geographic Artificial Intelligence (GeoAI), Large Language Models (LLMs), Vision-Language Models (VLMs), and multi-agent reasoning for intelligent civic data analysis. The proposed framework employs a multimodal perception module, a GeoFusion Transformer for spatial-semantic representation learning, and a GIS-enhanced Retrieval-Augmented Generation (RAG) module to identify urban issues, detect spatial hotspots, and generate explainable planning recommendations. Experimental results on the multimodal urban participation dataset demonstrate that GeoCivic-Agent achieves an F1-score of 94.6% for urban issue classification, outperforming the GPT-based single-agent baseline by 2.8 percentage points. For spatial hotspot detection, the proposed framework obtains an AUC of 96.2% and reduces MAE to 0.087, showing superior capability in discovering urban concern patterns and generating reliable spatial intelligence compared with existing GeoAI and LLM-based approaches.
References
[1] Goodchild, Sarah A., et al. "A humanised murine monoclonal antibody with broad serogroup specificity protects mice from challenge with Venezuelan equine encephalitis virus." Antiviral research 90.1 (2011): 1-8.
[2] Janowicz, Krzysztof, et al. "GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond." International Journal of Geographical Information Science 34.4 (2020): 625-636.
[3] Yang, Ruiyi, Yanfei Zhong, and Yu Su. "Self-supervised joint representation learning for urban land-use classification with multisource geographic data." IEEE Transactions on Geoscience and Remote Sensing 63 (2025): 1-21.
[4] Yuan, Long, et al. "Omnigeo: Towards a multimodal large language models for geospatial artificial intelligence." arXiv preprint arXiv:2503.16326 (2025).
[5] Radford, Alec, et al. "Learning transferable visual models from natural language supervision." International conference on machine learning. PmLR, 2021.
[6] Huang, Weiming, Jing Wang, and Gao Cong. "Zero-shot urban function inference with street view images through prompting a pretrained vision-language model." International Journal of Geographical Information Science 38.7 (2024): 1414-1442.
[7] Xu, Jinwen, and Ran Tao. "Map reading and analysis with GPT-4V (ision)." ISPRS International Journal of Geo-Information 13.4 (2024): 127.
[8] Zhou, Zhilun, et al. "Large language model for participatory urban planning." arXiv preprint arXiv:2402.17161 (2024).
[9] Zhu, He, et al. "PlanGPT: Enhancing urban planning with tailored language model and efficient retrieval." arXiv preprint arXiv:2402.19273 (2024).
[10] Lee, Yesung, et al. "Applications of AI Large Language Models in Citizen Participatory Urban Planning: Using GPT-4o and Prompt Engineering." Journal of Korea Planning Association 60.4 (2025): 148-172.
[11] Park, Joon Sung, et al. "Generative agents: Interactive simulacra of human behavior." Proceedings of the 36th annual acm symposium on user interface software and technology. 2023.
[12] Howell, Anthony, et al. "Multimodal large language models, street view images and urban policy-intelligence: recovering the sustainability effects of redlining." npj Urban Sustainability (2026).
[13] Yao, Yilin, et al. "Deep Learning Models for Multi-class Pneumonia Detection in Chest X-rays: A Comparative Study of VGG16, MobileNet, and ResNet152." Journal of Technology Innovation and Engineering 1.4 (2025).
[14] Qiu, Min, Linting Wu, and Shanshan Wang. "CyberDQFormer: A Knowledge Graph-Enhanced Transformer Framework for Security-Aware Data Quality Anomaly Detection and Autonomous Repair Against Network Attacks." Fundamental Scientific Reports in Multidisciplinary Areas 2.3 (2026): 34-52.
[15] Zhang, Bingli, et al. "Consensus Matrix: A Role-Specialized Multi-Agent Framework for Structured Collaborative Decision-Making in Agentic Visual Media Workflows." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026.
[16] Gao, Ziyang, Yuanliang Qu, and Yi Han. "Cross-Lingual Sponsored Search via Dual-Encoder and Graph Neural Networks for Context-Aware Query Translation in Advertising Platforms." arXiv preprint arXiv:2510.22957 (2025).
[17] Ren, Xingcheng. "Optimizing Large-Scale AI Server Testing via Adaptive Evolutionary Algorithms." International Journal of Computer Science and Engineering 1.4 (2026): 7-14.
[18] Hua, Zonghui, Yue Luo, and Yunting Ling. "LPG-SAC-TCO: A Large Language Model--Policy-Guided Soft Actor-Critic Framework for Total Cost of Ownership--Optimal Energy Management of Hydrogen Fuel Cell Heavy-Duty Trucks." European Journal of AI, Computing & Informatics 2.3 (2026): 1-11.
[19] Han, Zihan, Lingran Meng, and Jingwei Zhang. "A distributed hierarchical spatio-temporal edge-enhanced graph neural network for city-scale dynamic logistics routing." arXiv preprint arXiv:2512.18441 (2025).
[20] Zhang, Jingsi, and Jixiang Ding. "CA-PPO-AXI: Coverage-Aware Deep Reinforcement Learning for Adaptive AXI Bus Protocol Verification." Fundamental Scientific Reports in Multidisciplinary Areas 2.02 (2026): 159-169.
[21] Xu, Chengde, Chongye Wang, and Zeyu Li. "H2-LBM: A Hierarchical Hybrid Deep Reinforcement Learning Framework for L7 Load Balancing and Global Traffic Scheduling in Multi-Cloud LLM Serving." Fundamental Scientific Reports in Multidisciplinary Areas 2.02 (2026): 109-120.
[22] Ren, Xingcheng. "Research on Stress Testing Automation of AI Server for High Concurrency Scenarios." Journal of Intelligence and Engineering Technology 1.2 (2026): 7-12.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Wenfang Lu, Pinghao Luo

This work is licensed under a Creative Commons Attribution 4.0 International License.
License Terms (Recommended – CC BY 4.0)
All articles published in Fundamental Scientific Reports in Multidisciplinary Areas are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author(s) and source are properly cited. Users are allowed to copy, redistribute, remix, transform, and build upon the material for any purpose, including commercial use, as long as appropriate credit is given.
Authors retain copyright of their work while granting the journal the right of first publication. The journal provides immediate open access to its content on the principle that making research freely available supports a greater global exchange of knowledge.
For more information about this license, visit:
https://creativecommons.org/licenses/by/4.0/