UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization

arXiv 2507.04706 ↗First posted 7 Jul 2025cs.LG cs.AIcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 40 of its 89 references that are in the map. First posted on arXiv 7 Jul 2025.

Builds on

40 of 89 references.

Closest ancestors · 1

Same direction, newest first

2025A Survey of Personalization: From RAG to Agent14 Apr

Other references · 39

2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
2022MegaBlocks: Efficient Sparse Training with Mixture-of-Expertscited by 204
2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
2021Towards artificial general intelligence via a multimodal foundation modelcited by 112
2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 95
2023Levels of AGI for Operationalizing Progress on the Path to AGIcited by 94
2022From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectorscited by 82
2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74

27 more

2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 69
2024Reinforcement Learning Enhanced LLMs: A Surveycited by 69
2019Toward Understanding Catastrophic Forgetting in Continual Learningcited by 67
2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learningcited by 51
2023RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarioscited by 46
2021TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learningcited by 42
2018Robust Optimization over Multiple Domainscited by 34
2020Efficient Architecture Search for Continual Learningcited by 34
2023Artificial General Intelligence for Medical Imaging Analysiscited by 32
2019Efficient Continual Learning in Neural Networks with Embedding Regularizationcited by 20
2024Evaluation of RAG Metrics for Question Answering in the Telecom Domaincited by 19
2025RAG-Enhanced Collaborative LLM Agents for Drug Discoverycited by 18
2023TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Trainingcited by 15
2024Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Datacited by 14
2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
2022Asynchronous Distributed Bilevel Optimizationcited by 13
2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalizationcited by 12
2024Continual Learning for Smart City: A Surveycited by 9
2025Research on the Online Update Method for Retrieval-Augmented Generation (RAG) Model with Incremental Learningcited by 4
2024A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learningcited by 3
2025Cellular Traffic Prediction via Deep State Space Models with Attention Mechanismcited by 3
2021A Bilevel Programming Framework for Joint Edge Resource Management and Pricingcited by 2
2025MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Predictioncited by 2
2025Anomaly Detection in Event-triggered Traffic Time Series via Similarity Learningcited by 2
2025Adaptive Robust Optimization Models for DER Planning in Distribution Networks under Long- and Short-Term Uncertaintiescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way