用多智能体框架让大模型自动找热门路线，无需重训练。
CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query
- 设计双阶段多智能体系统，分步解决热门路径发现与生成。
- 在真实与合成数据上，路径识别准确率优于传统方法。
- 适合城市规划、导航优化等需要动态路径分析的场景。
热门路径查询——从历史轨迹数据中识别出两地间最常通行的路线——在城市规划、导航优化和旅行推荐中具有重要应用。传统算法和机器学习方法虽已取得成效，但通常需模型训练、参数调优，并在数据更新时重新训练。随着大语言模型（LLMs）在空间与图结构推理方面能力增强，其在地理空间问题中的应用日益受到关注。本文提出CompassLLM，一种新颖的多智能体框架，将LLM的推理能力融入地理空间领域以解决热门路径查询问题。CompassLLM采用两阶段流水线：第一阶段为SEARCH，用于识别热门路径；第二阶段为GENERATE，用于在历史轨迹中无对应路径时合成新路径。在真实与合成数据集上的实验表明，CompassLLM在SEARCH阶段表现更优，在GENERATE阶段也具备竞争力，同时具备成本效益。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。