Author name: Yifan Du, Zikang Liu, Jinbiao Peng, Jie Wu, Junyi Li, Jinyang Li, Wayne Xin Zhao, Ji-Rong Wen

arXiv:2604.12890v2 Announce Type: replace-cross
Abstract: Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous information and high…

arXiv:2604.12890v1 Announce Type: cross
Abstract: Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous information and high token c…