CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and Language

Abstract

Large Language Models (LLMs) offer new opportunities for the next Point-Of-Interest (POI) prediction task, leveraging their capabilities in semantic understanding of POI trajectories. However, previous LLM-based methods, which are superficially adapted to next POI prediction, largely overlook critical challenges associated with applying LLMs to this task. Specifically, LLMs encounter two critical challenges: (1) a lack of intrinsic understanding of numeric spatiotemporal data, which hinders accurate modeling of users' spatiotemporal distributions and preferences; and (2) an excessively large and unconstrained candidate POI space, which often results in random or irrelevant predictions. To address these issues, we propose a Collaborative Multi Agent Framework for Next POI Prediction, named CoMaPOI. Through the close interaction of three specialized agents (Profiler, Forecaster, and Predictor), CoMaPOI collaboratively addresses the two critical challenges. The Profiler agent is responsible for converting numeric data into language descriptions, enhancing semantic understanding. The Forecaster agent focuses on dynamically constraining and refining the candidate POI space. The Predictor agent integrates this information to generate high-precision predictions. Extensive experiments on three benchmark datasets (NYC, TKY, and CA) demonstrate that CoMaPOI achieves state of the art performance, improving all metrics by 5% to 10% compared to SOTA baselines. This work pioneers the investigation of challenges associated with applying LLMs to complex spatiotemporal tasks by leveraging tailored collaborative agents.

This paper has been accepted by SIGIR 2025

References in corpus (11)

• Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
• GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
• The Power of Noise: Redefining Retrieval for RAG Systems
• Point-of-Interest Recommender Systems based on Location-Based Social Networks: A Survey from an Experimental Perspective
• Large Language Models for Next Point-of-Interest Recommendation
• Graph Masked Autoencoder for Sequential Recommendation
• ST-PIL: Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation
• Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning
• ToolQA: A Dataset for LLM Question Answering with External Tools
• DiffuRec: A Diffusion Model for Sequential Recommendation
• LLMLight: Large Language Models as Traffic Signal Control Agents

Cited by in corpus (1)

• Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems