@article{capnavbenchmarkingvisionlanguagemodelson,
  title = {CapNav: Benchmarking Vision Language Models on Capability-conditioned Indoor Navigation},
  author = {Xia Su and Ruiqi Chen and Benlin Liu and Jingwei Ma and Zonglin Di and Ranjay Krishna and Jon Froehlich},
  year = {2026},
  eprint = {2602.18424},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.18424},
}