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

TL;DR

This paper introduces CoMaPOI, a multi-agent framework that enhances POI prediction by combining semantic understanding and candidate space refinement, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents a novel multi-agent framework that effectively addresses LLM limitations in spatiotemporal data understanding for POI prediction.

Findings

Achieves 5-10% improvement over SOTA baselines.

Effectively constrains candidate POI space for better accuracy.

Demonstrates the effectiveness of specialized agents in LLM-based tasks.

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.