# Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation

arXiv: https://arxiv.org/abs/2506.21599 · HTML: https://mlsanity.com/paper/2506.21599/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [Where Would I Go Next? Large Language Models as Human Mobility Predictors](https://mlsanity.com/paper/2308.15197/) (2023)
- [Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2404.17591/) (2024)
- [A Large Language Model Enhanced Conversational Recommender System](https://mlsanity.com/paper/2308.06212/) (2023)
- [Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation](https://mlsanity.com/paper/2404.01855/) (2024)
- [Generative Next POI Recommendation with Semantic ID](https://mlsanity.com/paper/2506.01375/) (2025)
- [CoMaPOI: A Collaborative Multi-Agent Framework for Next POI Prediction Bridging the Gap Between Trajectory and Language](https://mlsanity.com/paper/2505.23837/) (2025)
- [GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender Systems](https://mlsanity.com/paper/2410.20643/) (2024)

## Built on by (most cited first, 2 of 2)

- [Think2Go: Generative Next POI Recommendation with LLM Reasoning](https://mlsanity.com/paper/2607.28997/) (2026)
- [SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation](https://mlsanity.com/paper/2608.30399/) (2026)

## Abstract (arXiv)

Advancing large language models (LLMs) for the next point-of-interest (POI) recommendation task faces two fundamental challenges: (i) although existing methods produce semantic IDs that incorporate semantic information, their topology-blind indexing fails to preserve semantic continuity, meaning that proximity in ID values does not mirror the coherence of the underlying semantics; and (ii) supervised fine-tuning (SFT)-based methods restrict model outputs to top-1 predictions. These approaches suffer from "answer fixation" and neglect the need for top-k ranked lists and reasoning due to the scarcity of supervision. We propose Refine-POI, a framework that addresses these challenges through topology-aware ID generation and reinforcement fine-tuning. First, we introduce a hierarchical self-organizing map (SOM) quantization strategy to generate semantic IDs, ensuring that coordinate proximity in the codebook reflects semantic similarity in the latent space. Second, we employ a policy-gradient framework to optimize the generation of top-k recommendation lists, liberating the model from strict label matching. Extensive experiments on three real-world datasets demonstrate that Refine-POI significantly outperforms state-of-the-art baselines, effectively synthesizing the reasoning capabilities of LLMs with the representational fidelity required for accurate and explainable next-POI recommendation.