@inproceedings{wang-etal-2026-think,
    title = "Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3{D} Visual Grounding",
    author = "Wang, Haibo  and
      Lin, Zihao  and
      Xu, Zhiyang  and
      Huang, Lifu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.649/",
    pages = "14935--14953",
    ISBN = "979-8-89176-459-0"
}