Smart City Gnosys
Smart city article details
| Title | Llm Agents For Smart City Management: Enhancing Decision Support Through Multi-Agent Ai Systems |
|---|---|
| ID_Doc | 35404 |
| Authors | Kalyuzhnaya A.; Mityagin S.; Lutsenko E.; Getmanov A.; Aksenkin Y.; Fatkhiev K.; Fedorin K.; Nikitin N.O.; Chichkova N.; Vorona V.; Boukhanovsky A. |
| Year | 2025 |
| Published | Smart Cities, 8, 1 |
| DOI | http://dx.doi.org/10.3390/smartcities8010019 |
| Abstract | Highlights: What are the main findings? For smart city management, LLM-based multi-agent systems achieve 94–99% accuracy in routing urban queries and demonstrate significant improvements in response quality (G-Eval scores of 0.68–0.74) compared to standalone LLMs (0.30–0.38). Achievement of high scores in routing queries and response accuracy is possible with middle-size LLM models rather than the biggest LLM models. What is the implication of the main findings? The multi-agent LLM approach enables efficient processing of complex urban planning tasks while maintaining high relevance in responses, making it practical for real-world city management applications. LLM agents can effectively augment human decision making in urban planning by reducing task completion time from days to hours while maintaining accuracy and accountability in complex scenarios. This study investigates the implementation of LLM agents in smart city management, leveraging both the inherent language processing abilities of LLMs and the distributed problem solving capabilities of multi-agent systems for the improvement of urban decision making processes. A multi-agent system architecture combines LLMs with existing urban information systems to process complex queries and generate contextually relevant responses for urban planning and management. The research is focused on three main hypotheses testing: (1) LLM agents’ capability for effective routing and processing diverse urban queries, (2) the effectiveness of Retrieval-Augmented Generation (RAG) technology in improving response accuracy when working with local knowledge and regulations, and (3) the impact of integrating LLM agents with existing urban information systems. Our experimental results, based on a comprehensive validation dataset of 150 question–answer pairs, demonstrate significant improvements in decision support capabilities. The multi-agent system achieved pipeline selection accuracy of 94–99% across different models, while the integration of RAG technology improved response accuracy by 17% for strategic development queries and 55% for service accessibility questions. The combined use of document databases and service APIs resulted in the highest performance metrics (G-Eval scores of 0.68–0.74) compared to standalone LLM responses (0.30–0.38). Using St. Petersburg’s Digital Urban Platform as a testbed, we demonstrate the practical applicability of this approach to create integrated city management systems with support complex urban decision making processes. This research contributes to the growing field of AI-enhanced urban management by providing empirical evidence of LLM agents’ effectiveness in processing heterogeneous urban data and supporting strategic planning decisions. Our findings suggest that LLM-based multi-agent systems can significantly enhance the efficiency and accuracy of urban decision making while maintaining high relevance in responses. © 2025 by the authors. |
| Author Keywords | data-driven management; large language model; LLM; LLM agent; multi-agent system; smart city management; strategic management |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
7228  | 0.869 | Son T.H.; Weedon Z.; Yigitcanlar T.; Sanchez T.; Corchado J.M.; Mehmood R. | Algorithmic Urban Planning For Smart And Sustainable Development: Systematic Review Of The Literature | Sustainable Cities and Society, 94 (2023) |
| 32187 | 0.867 | Darwish D. | Integration Of Llms In Smart Cities For Sustainable Energy Solutions | Revolutionizing Urban Development and Governance With Emerging Technologies (2025) |
| 5340 | 0.861 | Shoaib M.R.; Emara H.M.; Zhao J. | A Survey On The Applications Of Frontier Ai, Foundation Models, And Large Language Models To Intelligent Transportation Systems | ICCA 2023 - 2023 5th International Conference on Computer and Applications, Proceedings (2023) |
| 16010 | 0.861 | Yigitcanlar T.; Desouza K.C.; Butler L.; Roozkhosh F. | Contributions And Risks Of Artificial Intelligence (Ai) In Building Smarter Cities: Insights From A Systematic Review Of The Literature | Energies, 13, 6 (2020) |
| 10507 | 0.857 | dos Santos S.C.; Vilela J.F.F.; Carvalho T.H.; Rocha T.C.; Candido T.B.; Bezerra V.S.; Silva D.J. | Artificial Intelligence In Sustainable Smart Cities: A Systematic Study On Applications, Benefits, Challenges, And Solutions | International Conference on Enterprise Information Systems, ICEIS - Proceedings, 1 (2024) |
| 8443 | 0.857 | Huang Y.; Zhou M.; Deng R.; Huang Z.; You L. | An Integrated Framework For Population Synthesis At Fine-Grained Spatial Scales | Lecture Notes in Civil Engineering, 211 LNCE (2023) |
| 37589 | 0.857 | Lom, M; Pribyl, O | Modeling Of Smart City Building Blocks Using Multi-Agent Systems | NEURAL NETWORK WORLD, 27, 4 (2017) |
| 50448 | 0.857 | Mortaheb R.; Jankowski P. | Smart City Re-Imagined: City Planning And Geoai In The Age Of Big Data | Journal of Urban Management, 12, 1 (2023) |
| 13108 | 0.857 | Karger E.; Rothweiler A.; Brée T.; Ahlemann F. | Building The Smart City Of Tomorrow: A Bibliometric Analysis Of Artificial Intelligence In Urbanization | Urban Science, 9, 4 (2025) |
| 6945 | 0.856 | Rodriguez E.; Edwards J.S. | Ai In Smart Cities Development: A Perspective Of Strategic Risk Management | European Conference on the Impact of Artificial Intelligence and Robotics, ECIAIR 2019 (2019) |