# RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking

arXiv: https://arxiv.org/abs/2509.17066 · HTML: https://mlsanity.com/paper/2509.17066/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation.
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 21 Sep 2025.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [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)
- [Large Language Models are Zero-Shot Next Location Predictors](https://mlsanity.com/paper/2405.20962/) (2024)
- [Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation](https://mlsanity.com/paper/2404.01855/) (2024)
- [Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysis](https://mlsanity.com/paper/2501.17598/) (2025)

## Built on by (most cited first, 3 of 3)

- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [ActivityEditor: Learning to Synthesize Physically Valid Human Mobility](https://mlsanity.com/paper/2604.05529/) (2026)
- [ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery](https://mlsanity.com/paper/2608.18846/) (2026)

## Abstract (arXiv)

Next point-of-interest (POI) recommendation predicts a user's next destination from historical movements. Traditional models require intensive training, while LLMs offer flexible and generalizable zero-shot solutions but often generate generic or geographically irrelevant results due to missing trajectory and spatial context. To address these issues, we propose RALLM-POI, a framework that couples LLMs with retrieval-augmented generation and self-rectification. We first propose a Historical Trajectory Retriever (HTR) that retrieves relevant past trajectories to serve as contextual references, which are then reranked by a Geographical Distance Reranker (GDR) for prioritizing spatially relevant trajectories. Lastly, an Agentic LLM Rectifier (ALR) is designed to refine outputs through self-reflection. Without additional training, RALLM-POI achieves substantial accuracy gains across three real-world Foursquare datasets, outperforming both conventional and LLM-based baselines. Code is released at https://github.com/LKRcrocodile/RALLM-POI.