Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.04706 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916829794926592 |
|---|---|
| author | Yang, Kai Zhu, Zelin Jian, Chengtao Ma, Hui Zhao, Shengjie Ye, Xiaozhou Ouyang, Ye |
| author_facet | Yang, Kai Zhu, Zelin Jian, Chengtao Ma, Hui Zhao, Shengjie Ye, Xiaozhou Ouyang, Ye |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04706 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization Yang, Kai Zhu, Zelin Jian, Chengtao Ma, Hui Zhao, Shengjie Ye, Xiaozhou Ouyang, Ye Machine Learning Artificial Intelligence 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. |
| title | UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.04706 |