arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.07516cs.AIcs.CL
收藏

CompassLLM: 一种面向流行路径查询的多智能体方法

CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query

Bangladesh University of Engineering and Technology(孟加拉工程科技大学);University of Utah(犹他大学);Monash University(莫纳什大学);Qatar Computing Research Institute(卡塔尔计算研究所)

Md. Nazmul Islam Ananto, Shamit Fatin, Mohammed Eunus Ali, Md Rizwan Parvez

AI总结:

CompassLLM通过多智能体框架解决流行路径查询问题,结合空间推理能力提升搜索和生成性能,实验显示其在准确性和成本效益方面表现优异。

摘要:

流行路径查询——从历史轨迹数据中识别最频繁的路线——在城市规划、导航优化和旅行推荐中有重要应用。尽管传统算法和机器学习方法在该领域取得成功,但它们在数据更新时通常需要模型训练、参数调优和重新训练。随着大型语言模型(LLMs)在空间和图推理方面的能力不断增强,研究如何将这些模型应用于地理空间问题变得越来越重要。我们介绍了CompassLLM,一种新颖的多智能体框架,通过智能利用LLMs的推理能力进入地理空间领域以解决流行路径查询。CompassLLM采用两阶段流程:SEARCH阶段识别流行路径,GENERATE阶段在历史轨迹数据中没有现有路径时合成新路径。在真实和合成数据集上的实验表明,CompassLLM在SEARCH阶段表现出色,在GENERATE阶段具有竞争力,同时具有成本效益。

英文摘要:

The popular path query - identifying the most frequented routes between locations from historical trajectory data - has important applications in urban planning, navigation optimization, and travel recommendations. While traditional algorithms and machine learning approaches have achieved success in this domain, they typically require model training, parameter tuning, and retraining when accommodating data updates. As Large Language Models (LLMs) demonstrate increasing capabilities in spatial and graph-based reasoning, there is growing interest in exploring how these models can be applied to geo-spatial problems. We introduce CompassLLM, a novel multi-agent framework that intelligently leverages the reasoning capabilities of LLMs into the geo-spatial domain to solve the popular path query. CompassLLM employs its agents in a two-stage pipeline: the SEARCH stage that identifies popular paths, and a GENERATE stage that synthesizes novel paths in the absence of an existing one in the historical trajectory data. Experiments on real and synthetic datasets show that CompassLLM demonstrates superior accuracy in SEARCH and competitive performance in GENERATE while being cost-effective.

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。

↑