@article{espireadiagnosticbenchmarkforembodiedspa,
  title = {ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models},
  author = {Yanpeng Zhao and Wentao Ding and Hongtao Li and Baoxiong Jia and Zilong Zheng},
  year = {2026},
  eprint = {2603.13033},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.13033},
}