@inproceedings{zhang-etal-2024-omagent,
    title = "{O}m{A}gent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer",
    author = "Zhang, Lu  and
      Zhao, Tiancheng  and
      Ying, Heting  and
      Ma, Yibo  and
      Lee, Kyusong",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.559/",
    doi = "10.18653/v1/2024.emnlp-main.559",
    pages = "10031--10045"
}