@inproceedings{xu-etal-2026-citycube,
    title = "{C}ity{C}ube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments",
    author = "Xu, Haotian  and
      Hu, Yue  and
      Zhu, Zhengqiu  and
      Gao, Chen  and
      Wang, Ziyou  and
      Rao, Junreng  and
      Lu, Wenhao  and
      Li, Weishi  and
      Yin, Quanjun  and
      Li, Yong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.416/",
    pages = "9190--9215",
    ISBN = "979-8-89176-390-6",
    abstract = "Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique challenges of open-ended urban spaces characterized by rich semantics, complex geometries, and view variations. To address this, we introduce CityCube, a systematic benchmark designed to probe cross-view reasoning capabilities of current VLMs in urban settings. CityCube integrates four viewpoint dynamics to mimic camera movements and spans a wide spectrum of perspectives from multiple platforms, e.g., vehicles, drones and satellites. For a comprehensive assessment, it features 5,022 meticulously annotated multi-view QA pairs categorized into five cognitive dimensions and three spatial relation expressions. A comprehensive evaluation of 33 VLMs reveals a significant performance disparity with humans: even large-scale models struggle to exceed 54.1{\%} accuracy, remaining 34.2{\%} below human performance. By contrast, small-scale fine-tuned VLMs achieve over 60.0{\%} accuracy, highlighting the necessity of our benchmark. Further analyses indicate the task correlations and fundamental cognitive disparity between VLMs and human-like reasoning."
}