AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction

2024-08-26

AI Summary

To address the challenge of modeling complex mobility patterns and geographic knowledge in zero-shot next-location prediction—where large language models (LLMs) suffer from inherent limitations and geographic bias—this paper proposes the first decoupled multi-agent framework. It explicitly separates three core capabilities: individual spatiotemporal memory, city-structure knowledge generation, and collective pattern extraction, integrating them via a collaborative reasoning mechanism. This design overcomes the constraints of end-to-end LLM generation and substantially mitigates geographic bias. The framework is agnostic to LLM backbones—supporting both open- and closed-source models without fine-tuning. Evaluated on a dual-source trajectory dataset, it outperforms state-of-the-art methods on 8 of 12 metrics, with improvements ranging from 3.33% to 8.57%, and demonstrates strong cross-city generalization. The implementation is publicly available.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Zero-shot next location prediction
• Systematic agentic framework design
• Spatial-temporal and geospatial knowledge integration

Innovation

• Decomposed mobility prediction task
• Integrated spatial-temporal memory module
• Combined world knowledge generator module