@inproceedings{fang-etal-2026-video, title = "Video-{D}eep{R}esearch: Towards the Next-Generation Multimodal Deepresearch Agent", author = "Fang, Zhen and Zeng, Yu and Huang, Wenxuan and Zhao, Yiming and Huang, Shiting and Ren, Tianfei and Lu, Qi and Ren, Qingnan and Su, Qisheng and Wang, Lionel Z. and Yin, Qingyu and Chen, Shuang and Chen, Zehui and Chen, Lin and Yin, Zhenfei and Hu, Yao and Lin, Shaohui and Ouyang, Wanli and Cao, Shaosheng and Zhao, Feng", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.findings-emnlp.1881/", pages = "40113--40131", ISBN = "979-8-89176-462-0" }