mlsanityData to 14 Oct 2026

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

arXiv 2509.17066 ↗First posted 21 Sep 2025cs.AI cs.IRcited by 3

On the map: Retrieval-augmented generation → RAG for recommendation

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.

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.

Builds on

7 of 17 references.

References · 7

  1. 2017Attention Is All You Needcited by 60,361
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  3. 2023Where Would I Go Next? Large Language Models as Human Mobility Predictorscited by 93
  4. 2024Large Language Models for Next Point-of-Interest Recommendationcited by 40
  5. 2024Large Language Models are Zero-Shot Next Location Predictorscited by 22
  6. 2024Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendationcited by 17
  7. 2025Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysiscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Autonomous Information Seeking: A Roadmap for Agentic Recommender Systemscited by 4
  2. 2026ActivityEditor: Learning to Synthesize Physically Valid Human Mobilitycited by 0
  3. 2026ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Deliverycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation
  2. 2025Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction
  3. 2026ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
  4. 2026Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation
  5. 2023A Diffusion model for POI recommendation
  6. 2026An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark
  7. 2026Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation
  8. 2026Think2Go: Generative Next POI Recommendation with LLM Reasoning