@inproceedings{ma-etal-2026-tvir, title = "{TVIR}: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation", author = "Ma, Xinkai and Bai, Zhiqi and Zhang, Dingling and Liu, Pei and Yuan, Yishuo and Zhu, He and Wang, Jiakai and Xie, Qianqian and Zhao, Yifan and Yang, Xinlong and Cong, Hao and Yao, Zhiheng and Xie, Fengxia and Xu, Zihao and Xu, Haoran and Wang, Zhaohui and Liu, Minghao and Lin, Shirong and Tan, Yingshui and Xu, Yuchi and Su, Wenbo and Zhang, Zhaoxiang and Zheng, Bo and Liu, Jiaheng", 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.1530/", pages = "34918--34965", ISBN = "979-8-89176-459-0" }