# An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark

arXiv: https://arxiv.org/abs/2608.27840 · HTML: https://mlsanity.com/paper/2608.27840/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction](https://mlsanity.com/paper/2408.13986/) (2024)
- [Learning Points and Routes to Recommend Trajectories](https://mlsanity.com/paper/1608.07051/) (2016)
- [A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security](https://mlsanity.com/paper/2410.02191/) (2024)
- [A Survey of Point-of-interest Recommendation in Location-based Social Networks](https://mlsanity.com/paper/1607.00647/) (2016)
- [A Location-Sentiment-Aware Recommender System for Both Home-Town and Out-of-Town Users](https://mlsanity.com/paper/1706.06239/) (2017)
- [Out-of-Town Recommendation with Travel Intention Modeling](https://mlsanity.com/paper/2101.12555/) (2021)
- [SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation](https://mlsanity.com/paper/2506.01705/) (2025)
- [Learning Spatiotemporal Dynamical Systems from Point Process Observations](https://mlsanity.com/paper/2406.00368/) (2024)

## Abstract (arXiv)

Cross-city point-of-interest (POI) recommendation is crucial for navigating unfamiliar urban environments, yet its progress has historically been constrained by data limitations. Using the recently proposed large-scale benchmark Trip World, we empirically re-examine whether conclusions drawn on small prior benchmarks still hold under worldwide coverage, low home-destination region overlap, and large, semantically rich POI inventories. Our evaluation surfaces three bottlenecks of representative state-of-the-art methods: (1) hometown-aware models appear to rely more on destination-region priors than on user-specific preference transfer; (2) their accuracy-efficiency trade-off degrades at this scale, where the simplest model is among the strongest; and (3) existing mechanisms for integrating semantic metadata yield little benefit. We further include a diagnostic pilot on agentic methods adapted from next-POI recommendation, finding that naive adaptation trails a simple popularity prior even though the relevant semantic signal is present in the data. These results highlight the need for task-specific designs that support cross-city preference transfer, semantic grounding, and scalable reasoning over unseen destination inventories.