MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation
This addresses the need for better POI recommendations in location-based services, though it appears incremental as it applies existing multi-agent LLM concepts to an underexplored domain.
The paper tackles the problem of next Point-of-Interest (POI) recommendation by proposing MAS4POI, a multi-agent collaboration system using Large Language Models, and reports improved recommendation accuracy evaluated on two real-world datasets.
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.