@article{diveintothescenebreakingtheperceptualbot,
  title = {Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation},
  author = {Boyuan Xiao and Bohong Chen and Yumeng Li and Ji Feng and Yao-Xiang Ding and Kun Zhou},
  year = {2026},
  eprint = {2606.04046},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.04046},
}