MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation

Yuqian Wu, Yuhong Peng, Jiapeng Yu, Raymond S. T. Lee
9/5/2024
cs.IRcs.AIcs.SI

Official code: yuqian2003/MAS4POI (18 stars, MIT, last commit 2026-04-24).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

yuqian2003/MAS4POIOfficial100%
MIT

This repository hosts the official implementation of MAS4POI: A Multi-Agent System Collaboration for Next POI Recommendation, accepted by PAKDD 25.

185PythonAug 27, 20246 months agoMIT

Similar Papers

Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models

84% match2025

Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations

82% match2025

Knowledge Graph Enhanced Language Agents for Recommendation

81% match2024

A Survey on LLM-powered Agents for Recommender Systems

81% match1 repo12025

Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making

80% match2025

Customizing Language Models with Instance-wise LoRA for Sequential Recommendation

80% match1 repo262026

Cite this paper

@article{wu2024maspoi,
  title  = {MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation},
  author = {Yuqian Wu and Yuhong Peng and Jiapeng Yu and Raymond S. T. Lee},
  year   = {2024},
  eprint = {2409.13700},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.13700v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.13700.svg)](https://codeofpaper.com/paper/2409.13700)

Discussion