用多智能体协作提升下个地点推荐准确率。
MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation
- 设计四类专用智能体协同决策，分工处理数据、分析与导航。
- 在两个真实数据集上验证，推荐准确率显著优于基线方法。
- 适合对智能体系统和位置推荐感兴趣的开发者与研究者。
基于大语言模型的多智能体系统在复杂决策任务中展现出潜力，但在下一个兴趣点（POI）推荐领域的应用仍不充分。本文提出一种新型MAS4POI系统，通过多智能体协作提升下个POI推荐效果。该系统集成六种不同LLM，设置数据代理（DataAgent）、管理代理（Manager）、分析代理（Analyst）和导航代理（Navigator）四类专业化智能体，共同参与推荐生成过程。系统在两个真实世界数据集上进行评估，验证了其在现实场景中提升推荐准确率的有效性。代码已开源于https://github.com/yuqian2003/MAS4POI。
原文摘要 · Abstract (English)
LLM-based Multi-Agent Systems have potential benefits of complex decision-making tasks management across various domains but their applications in the next Point-of-Interest (POI) recommendation remain underexplored. This paper proposes a novel MAS4POI system designed to enhance next POI recommendations through multi-agent interactions. MAS4POI supports Large Language Models (LLMs) specializing in distinct agents such as DataAgent, Manager, Analyst, and Navigator with each contributes to a collaborative process of generating the next POI recommendations.The system is examined by integrating six distinct LLMs and evaluated by two real-world datasets for recommendation accuracy improvement in real-world scenarios. Our code is available at https://github.com/yuqian2003/MAS4POI.
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。