@article{structuringguielementsthroughvisionlangu,
  title = {Structuring GUI Elements through Vision Language Models: Towards Action Space Generation},
  author = {Yi Xu and Yesheng Zhang and Jiajia Liu and Jingdong Chen},
  year = {2025},
  eprint = {2508.16271},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.16271},
}