11:48
官方账号arXiv cs.AI@Hongcheng Gao, Hailong Qu, Jingyi Tang, Jiahao Wang, Zihao Huang, Hengkang Qiao, Shihong Huang, Junming Yang, Yi Li, Hongyixuan Yuan, Wenjie Li, Bohan Zeng, Wenbo Li, Bo Wang, Jianhui Liu, Olive Huang, Haoyang Huang, Wentao Zhang, Guoqing Huang, Nan Duan, Yinpeng Dong
精选
推荐理由：做多模态智能体或空间推理研究的团队，这个基准直接暴露了当前模型在真实交互任务上的短板——GPT-5都只有17.4%成功率，值得用来检验自家模型。