Bridging urban theory and artificial intelligence: a multi-agent recommendation system for sustainable city development
Связь между теорией города и искусственным интеллектом: мультиагентная рекомендательная система для устойчивого развития городов
2026-03-23
SCID: 54.1/qeh79dqw
Discuss with AI
classical urban theorieslarge language modelmulti-agent recommendation systemsustainable city developmenturban planning
Figures from the paper
Abstract (AI)
As cities increasingly rely on AI for sustainability challenges, a critical gap emerges: AI applications in urban planning and safety predominantly proceed without explicit guidance from established urban theories that have guided sustainable development for decades. Our analysis reveals that technology-driven research dominates the field, while problem-driven approaches addressing genuine urban needs remain minimal. To bridge this theory-practice disconnect, we develop a Large Language Model (LLM)-based multi-agent recommendation system [publicly available online] that realigns AI development with sustainable city principles. The system employs specialized agents to recommend appropriate theoretical frameworks, AI methods, and data sources for urban challenges, drawing from classical urban theories. Through diverse case studies, we demonstrate how our approach transforms technology-focused solutions into theory-grounded interventions that address sustainability’s interconnected dimensions. Our framework fundamentally shifts the question from “what can algorithms do?” to “what does this urban challenge require for sustainable outcomes?”—ensuring AI amplifies rather than replaces the theoretical wisdom essential for creating resilient, equitable, and livable cities that contribute to global sustainability targets.
Key Findings
1
Case studies show that the framework transforms technology-focused solutions into theory-grounded interventions for more resilient, equitable, and livable cities.
2
Specialized agents use classical urban theories to guide AI development toward sustainable city principles and interconnected sustainability dimensions.
3
Technology-driven AI research currently dominates urban planning and safety, while problem-driven approaches addressing genuine urban needs remain limited.
4
The proposed approach shifts urban AI design from asking what algorithms can do to identifying what each challenge requires for sustainable outcomes.
5
The study develops a publicly available LLM-based multi-agent recommendation system that connects urban challenges with suitable theories, AI methods, and data sources.
Research Object
LLM-based multi-agent recommendation system for sustainable city development
Research Subject
Alignment of AI development with classical urban theories to recommend theory-grounded AI methods and data sources for interconnected urban sustainability challenges
Publication Details
Publication Date
2026-03-23
Journal
Publisher
ISSN
Cited by
3
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
XGBoost2016
Semi-Supervised Classification with Graph Convolutional Networks2016
A Comprehensive Survey on Graph Neural Networks2020
Overcoming catastrophic forgetting in neural networks2017
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
Optimization Methods for Large-Scale Machine Learning2018
Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next2022
A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly2024
Research design: the methodology for interdisciplinary research framework2017
Clustering with t-SNE, Provably2019
Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories2025