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

arXiv: https://arxiv.org/abs/2505.23837 · HTML: https://mlsanity.com/paper/2505.23837/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 26 of 26)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [The Power of Noise: Redefining Retrieval for RAG Systems](https://mlsanity.com/paper/2401.14887/) (2024)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [ST-LLM: Large Language Models Are Effective Temporal Learners](https://mlsanity.com/paper/2404.00308/) (2024)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation](https://mlsanity.com/paper/2110.05730/) (2021)
- [DiffuRec: A Diffusion Model for Sequential Recommendation](https://mlsanity.com/paper/2304.00686/) (2023)
- [GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation](https://mlsanity.com/paper/2303.04741/) (2023)
- [IDGenRec: LLM-RecSys Alignment with Textual ID Learning](https://mlsanity.com/paper/2403.19021/) (2024)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System](https://mlsanity.com/paper/2404.11343/) (2024)
- [Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2404.17591/) (2024)
- [How Can Large Language Models Understand Spatial-Temporal Data?](https://mlsanity.com/paper/2401.14192/) (2024)
- [Leveraging LLM Reasoning Enhances Personalized Recommender Systems](https://mlsanity.com/paper/2408.00802/) (2024)
- [Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors](https://mlsanity.com/paper/2403.19347/) (2024)
- [RDRec: Rationale Distillation for LLM-based Recommendation](https://mlsanity.com/paper/2405.10587/) (2024)
- [Graph Masked Autoencoder for Sequential Recommendation](https://mlsanity.com/paper/2305.04619/) (2023)
- [Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation](https://mlsanity.com/paper/2212.08262/) (2022)
- [Point-of-Interest Recommender Systems based on Location-Based Social Networks: A Survey from an Experimental Perspective](https://mlsanity.com/paper/2106.10069/) (2021)
- [Urban Regional Function Guided Traffic Flow Prediction](https://mlsanity.com/paper/2303.09789/) (2023)
- [ST-PIL: Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2104.02262/) (2021)
- [Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation](https://mlsanity.com/paper/2403.12100/) (2024)

## Built on by (most cited first, 8 of 8)

- [Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review](https://mlsanity.com/paper/2506.01364/) (2025)
- [Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2506.21599/) (2025)
- [CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation](https://mlsanity.com/paper/2604.20845/) (2026)
- [Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding](https://mlsanity.com/paper/2604.17174/) (2026)
- [ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2604.20846/) (2026)
- [Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent](https://mlsanity.com/paper/2606.05130/) (2026)
- [Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation](https://mlsanity.com/paper/2605.11807/) (2026)
- [Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2609.14227/) (2026)

## Abstract (arXiv)

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.