arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.13986cs.LGcs.AIcs.CLcs.IR
收藏

AgentMove:基于大语言模型的零样本下一跳位置预测智能体框架

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

Tsinghua University(清华大学)

Jie Feng, Yuwei Du, Jie Zhao, Yong Li

AI总结:

针对现有LLM直接应用于零样本下一跳位置预测的局限性,提出系统性智能体框架AgentMove,通过分解任务并设计三个核心模块融合信息推理,实验表明其在多指标上超越基线,且鲁棒性强、地理偏差小。

摘要:

下一跳位置预测在各类现实应用中发挥着关键作用。近年来,由于现有深度学习方法存在局限性,研究者尝试将大语言模型(LLMs)应用于零样本下一跳位置预测任务。然而,这些方法直接使用LLMs生成最终输出,缺乏系统性设计,限制了LLMs挖掘复杂移动模式的潜力,也低估了其丰富的全球地理空间知识储备。在本文中,我们提出AgentMove——一个系统性的智能体预测框架,以实现通用的下一跳位置预测。在AgentMove中,我们首先分解移动预测任务,并设计特定模块来完成各子任务:用于挖掘个体移动模式的时空记忆模块、用于建模城市结构影响的世界知识生成器,以及用于捕捉群体共享模式的集体知识提取器。最后,我们结合三个模块的结果并执行推理步骤以生成最终预测。利用两个不同来源的移动数据进行的大量实验表明,AgentMove在12项指标中的8项上超越领先基线3.33%至8.57%;以不同LLMs为基础时表现出稳健的预测性能,且在不同城市间地理偏差更小。我们的代码可通过https://github.com/tsinghua-fib-lab/AgentMove获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑