# CityGPT: Empowering Urban Spatial Cognition of Large Language Models

arXiv: https://arxiv.org/abs/2406.13948 · HTML: https://mlsanity.com/paper/2406.13948/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 44 of its 57 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 30 of 44)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [GLM-130B: An Open Bilingual Pre-trained Model](https://mlsanity.com/paper/2210.02414/) (2022)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [Llemma: An Open Language Model For Mathematics](https://mlsanity.com/paper/2310.10631/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition](https://mlsanity.com/paper/2310.05492/) (2023)
- [Pre-Trained Language Models for Interactive Decision-Making](https://mlsanity.com/paper/2202.01771/) (2022)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Platypus: Quick, Cheap, and Powerful Refinement of LLMs](https://mlsanity.com/paper/2308.07317/) (2023)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Where Would I Go Next? Large Language Models as Human Mobility Predictors](https://mlsanity.com/paper/2308.15197/) (2023)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization](https://mlsanity.com/paper/2306.05064/) (2023)
- [StepGame: A New Benchmark for Robust Multi-Hop Spatial Reasoning in Texts](https://mlsanity.com/paper/2204.08292/) (2022)

## Built on by (most cited first, 30 of 30)

- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning](https://mlsanity.com/paper/2410.16162/) (2024)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction](https://mlsanity.com/paper/2408.13986/) (2024)
- [BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysis](https://mlsanity.com/paper/2412.00953/) (2024)
- [A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science](https://mlsanity.com/paper/2504.09848/) (2025)
- [Diffusion Transformers as Open-World Spatiotemporal Foundation Models](https://mlsanity.com/paper/2411.12164/) (2024)
- [SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence](https://mlsanity.com/paper/2505.12703/) (2025)
- [CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?](https://mlsanity.com/paper/2512.16755/) (2025)
- [UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Prediction](https://mlsanity.com/paper/2411.12972/) (2024)
- [CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing](https://mlsanity.com/paper/2506.00530/) (2025)
- [UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective](https://mlsanity.com/paper/2509.22228/) (2025)
- [Graph World Models: Concepts, Taxonomy, and Future Directions](https://mlsanity.com/paper/2604.27895/) (2026)
- [USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents](https://mlsanity.com/paper/2505.17572/) (2025)
- [MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale](https://mlsanity.com/paper/2506.01297/) (2025)
- [CAMS: A CityGPT-Powered Agentic Framework for Urban Human Mobility Simulation](https://mlsanity.com/paper/2506.13599/) (2025)
- [Geospatial Mechanistic Interpretability of Large Language Models](https://mlsanity.com/paper/2505.03368/) (2025)
- [Damba-ST: Domain-Adaptive Mamba for Efficient Urban Spatio-Temporal Prediction](https://mlsanity.com/paper/2506.18939/) (2025)
- [Real-time Spatial Retrieval Augmented Generation for Urban Environments](https://mlsanity.com/paper/2505.02271/) (2025)
- [GeoResponder: Towards Building Geospatial LLMs for Time-Critical Disaster Response](https://mlsanity.com/paper/2509.19354/) (2025)
- [Enhancing Demand-Oriented Regionalization with Agentic AI and Local Heterogeneous Data for Adaptation Planning](https://mlsanity.com/paper/2511.10857/) (2025)
- [Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention](https://mlsanity.com/paper/2512.11811/) (2025)
- [ARMove: Learning to Predict Human Mobility through Agentic Reasoning](https://mlsanity.com/paper/2604.17419/) (2026)
- [A Dataset for Spatiotemporal-Sensitive POI Question Answering](https://mlsanity.com/paper/2505.10928/) (2025)
- [From Time Series Analysis to Question Answering: A Survey in the LLM Era](https://mlsanity.com/paper/2506.11512/) (2025)
- [UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics](https://mlsanity.com/paper/2606.15890/) (2026)
- [EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation](https://mlsanity.com/paper/2607.22655/) (2026)
- [Can Urban Blight Be Accessed with Vision-language Models: A Case Study in Detroit](https://mlsanity.com/paper/2608.01753/) (2026)
- [USAI-Quant: A Quantitative Reasoning Benchmark for Vision-Language Models in Built Environments](https://mlsanity.com/paper/2609.32813/) (2026)
- [Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models](https://mlsanity.com/paper/2610.16769/) (2026)

## Abstract (arXiv)

Large language models(LLMs), with their powerful language generation and reasoning capabilities, have already achieved notable success in many domains, e.g., math and code generation. However, they often fall short when tackling real-life geospatial tasks within urban environments. This limitation stems from a lack of physical world knowledge and relevant data during training. To address this gap, we propose textitCityGPT, a systematic framework designed to enhance LLMs' understanding of urban space and improve their ability to solve the related urban tasks by integrating a city-scale `world model' into the model. Firstly, we construct a diverse instruction tuning dataset, textitCityInstruction, for injecting urban knowledge into LLMs and effectively boosting their spatial reasoning capabilities. Using a combination of textitCityInstruction and open source general instruction data, we introduce a novel and easy-to-use self-weighted fine-tuning method (textitSWFT) to train various LLMs (including ChatGLM3-6B, Llama3-8B, and Qwen2.5-7B) to enhance their urban spatial capabilities without compromising, or even improving, their general abilities. Finally, to validate the effectiveness of our proposed framework, we develop a comprehensive text-based spatial benchmark textitCityEval for evaluating the performance of LLMs across a wide range of urban scenarios and geospatial tasks. Extensive evaluation results demonstrate that smaller LLMs trained with textitCityInstruction by textitSWFT method can achieve performance that is competitive with, and in some cases superior to, proprietary LLMs when assessed using textitCityEval.