UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models

TL;DR

UrbanLLM is a specialized large language model designed to autonomously address complex urban planning and management problems by decomposing queries and leveraging spatio-temporal AI models, outperforming existing LLMs in urban scenarios.

Contribution

This paper introduces UrbanLLM, a fine-tuned LLM that autonomously decomposes urban queries and integrates spatio-temporal AI models, advancing urban activity planning capabilities.

Findings

UrbanLLM outperforms Llama and GPT series in urban problem-solving.

UrbanLLM reduces human workload in urban planning tasks.

UrbanLLM demonstrates high effectiveness in complex urban scenarios.

Abstract

Location-based services play an critical role in improving the quality of our daily lives. Despite the proliferation of numerous specialized AI models within spatio-temporal context of location-based services, these models struggle to autonomously tackle problems regarding complex urban planing and management. To bridge this gap, we introduce UrbanLLM, a fine-tuned large language model (LLM) designed to tackle diverse problems in urban scenarios. UrbanLLM functions as a problem-solver by decomposing urban-related queries into manageable sub-tasks, identifying suitable spatio-temporal AI models for each sub-task, and generating comprehensive responses to the given queries. Our experimental results indicate that UrbanLLM significantly outperforms other established LLMs, such as Llama and the GPT series, in handling problems concerning complex urban activity planning and management. UrbanLLM exhibits considerable potential in enhancing the effectiveness of solving problems in urban scenarios, reducing the workload and reliance for human experts.