UrbanLLM: Autonomous Urban Activity Planning and Management with Large Language Models
This addresses the problem of inefficient urban activity planning for location-based services, though it appears incremental as it builds on existing LLMs and AI models.
The paper tackles the challenge of autonomous urban planning and management by introducing UrbanLLM, a fine-tuned large language model that decomposes queries into sub-tasks and uses spatio-temporal AI models, resulting in significant outperformance over other LLMs like Llama and GPT series in handling complex urban problems.
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.