Shi, Yongxin, Jiapeng Wang, Zeyu Shan, Dezhi Peng, Zening Lin, and Lianwen Jin. “URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 30 (March 14, 2026): 25357–25365. Accessed May 14, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/39729.