Real-world navigation is fundamentally driven by Points of Interest (POIs), yet reaching a precise POI remains a critical "final-meters" challenge. Existing Vision-Language Navigation (VLN) benchmarks of POI-goal navigation often suffer from coarse granularity or significant sim-to-real gaps due to generated scene. To bridge this gap, we present POINav-Bench, the first benchmark designed for closed-loop evaluation of real-world POI-goal navigation. It comprises 11 commercial areas reconstructed from real-world captures using 3D Gaussian Splatting (3DGS), covering 126,398 m2 in total and spanning 163 distinct POIs. With traversability-aware annotations and reference trajectories, POINav-Bench enables high-fidelity evaluation of navigation agents in realistic, POI-rich real-world environments. Building on this, we propose the POINav Brain-Action Framework where a Brain module performs POI-grounded reasoning to guide an Action module in predicting continuous waypoints for real-world execution. We further curate the POINav-Dataset, containing 70K real-world signage-entrance pairs. Experiments show that our framework provides a viable path toward refining real-world POI-goal navigation.
@article{arxiv.2605.28237,
title = {POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation},
author = {Ruiyan Gong and Meisheng Zhang and Yuxiang Zhao and Mingchao Sun and Yanfen Shen and Zedong Chu and Zhining Gu and Wei Guo and Xiaolong Cheng and Qiming Li and Kangning Niu and Yanqing Zhu and Xiaolong Wu and Tianlun Li and Mu Xu},
journal= {arXiv preprint arXiv:2605.28237},
year = {2026}
}