@inproceedings{zhou-etal-2026-videoagent, title = "{V}ideo{A}gent: All-in-One Framework for Video Understanding and Editing", author = "Zhou, Hengji and Huang, Lingxuan and Wang, Jian and Zhou, Bing and Wu, Si and Xia, Lianghao and Huang, Chao", 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.949/", pages = "21860--21906", ISBN = "979-8-89176-459-0" }