UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization
Authors:
- Kai YangKYKai Yang
- Zelin ZhuZZZelin Zhu
- Chengtao JianCJChengtao Jian
- Hui MaHMHui Ma
- Shengjie ZhaoShengjie Zhao
- Xiaozhou YeXYXiaozhou Ye
- Ye OuyangYOYe Ouyang
Preprint
Abstract
Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented generation (RAG) framework designed to facilitate UGI. Central to UrbanMind is a novel architecture based on Continual Retrieval-Augmented MoE-based LLM (C-RAG-LLM), which dynamically incorporates domain-specific knowledge and evolving urban data to support long-term adaptability. The architecture of C-RAG-LLM aligns naturally with a multilevel optimization framework, where different layers are treated as interdependent sub-problems. Each layer has distinct objectives and can be optimized either independently or jointly through a hierarchical learning process. The framework is highly flexible, supporting both end-to-end training and partial layer-wise optimization based on resource or deployment constraints. To remain adaptive under data drift, it is further integrated with an incremental corpus updating mechanism. Evaluations on real-world urban tasks of a variety of complexity verify the effectiveness of the proposed framework. This work presents a promising step toward the realization of general-purpose LLM agents in future urban environments.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Adaptive robust optimization models for DER planning in distribution networks under long- and short-term uncertaintiesApplied Energy, 2026
- Cellular traffic prediction via deep state space models with attention mechanismComputer Communications, 2022
- Fusion of engineering insights and emerging trends: Intelligent urban traffic management systemInformation Fusion, 2022
- Systematic literature review of context-awareness applications supported by smart cities’ infrastructuresSN Applied Sciences, 2022
- Machine learning‐based traffic scheduling techniques for intelligent transportation system: Opportunities and challengesInternational Journal of Communication Systems, 2021
- City intelligence for enhancing urban performance value: a conceptual study on data decomposition in smart citiesAsia-Pacific Journal of Regional Science, 2021
- Continual learning for robotics: Definition, framework, learning strategies, opportunities and challengesInformation Fusion, 2020
- MARES: multitask learning algorithm for Web-scale real-time event summarizationWorld Wide Web, 2018
- Distributed robust optimization (DRO), part I: framework and exampleOptimization and Engineering, 2012
- The Wasserstein distance and approximation theoremsProbability Theory and Related Fields, 1985