AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction
This work addresses the challenge of predicting future locations in mobility applications, offering a more systematic approach than prior LLM-based methods, though it appears incremental as it builds on existing LLM applications in this domain.
The paper tackles the problem of zero-shot next location prediction by introducing AgentMove, a systematic agentic framework that decomposes the task into modules for mining individual patterns, modeling urban structure, and capturing shared population patterns, achieving improvements of 3.33% to 8.57% over leading baselines across most metrics.
Next location prediction plays a crucial role in various real-world applications. Recently, due to the limitation of existing deep learning methods, attempts have been made to apply large language models (LLMs) to zero-shot next location prediction task. However, they directly generate the final output using LLMs without systematic design, which limits the potential of LLMs to uncover complex mobility patterns and underestimates their extensive reserve of global geospatial knowledge. In this paper, we introduce AgentMove, a systematic agentic prediction framework to achieve generalized next location prediction. In AgentMove, we first decompose the mobility prediction task and design specific modules to complete them, including spatial-temporal memory for individual mobility pattern mining, world knowledge generator for modeling the effects of urban structure and collective knowledge extractor for capturing the shared patterns among population. Finally, we combine the results of three modules and conduct a reasoning step to generate the final predictions. Extensive experiments utilizing mobility data from two distinct sources reveal that AgentMove surpasses the leading baseline by 3.33% to 8.57% across 8 out of 12 metrics and it shows robust predictions with various LLMs as base and also less geographical bias across cities. Our codes are available via https://github.com/tsinghua-fib-lab/AgentMove.