TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation
Dongsheng Wang, Shen Gao, Chengrui Huang, Yuxi Huang, Ruixiang Feng, Shuo Shang

TL;DR
Tool4POI introduces a tool-augmented LLM framework for POI recommendation that effectively handles out-of-history scenarios and scales to large candidate sets without task-specific fine-tuning.
Contribution
It presents a novel external retrieval and reasoning framework for LLM-based POI recommendation, addressing key limitations of existing methods.
Findings
Achieves up to 40% accuracy in OOH scenarios.
Outperforms state-of-the-art baselines in accuracy metrics.
Does not require task-specific fine-tuning.
Abstract
Next Point-of-Interest (POI) recommendation is a fundamental task in location-based services. While recent advances leverage Large Language Model (LLM) for sequential modeling, existing LLM-based approaches face two key limitations: (i) strong reliance on the contextual completeness of user histories, resulting in poor performance on out-of-history (OOH) scenarios; (ii) limited scalability, due to the restricted context window of LLMs, which limits their ability to access and process a large number of candidate POIs. To address these challenges, we propose Tool4POI, a novel tool-augmented framework that enables LLMs to perform open-set POI recommendation through external retrieval and reasoning. Tool4POI consists of three key modules: preference extraction module, multi-turn candidate retrieval module, and reranking module, which together summarize long-term user interests, interact…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsRecommender Systems and Techniques · Human Mobility and Location-Based Analysis · Multimodal Machine Learning Applications
