以下为上游提供的源文稿,可能存在识别错误。
乔木转写是基于源文稿的中文提炼,不是逐字翻译。请核对原文中的人名、数字与观点。
选一篇,慢慢读
从左侧挑一篇,正文会在这里排成书页。
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D graphical interfaces a
阅读原文 · Run Luo, Kuan Zhang, Qi Deng, Yukun Chen, Zhihao Yang, Yufei Zhang, Renrong Hu, Yi Zhang, Guiyu Ma, Tianyu Fan, Longze Chen, Hao Sun, Jiaming Li, Jiaming Yang, Xiaohao Liu, Tao Tan, Minzheng Wang, Hangtian Jia, Shuai Yuan, Lvdi Wang, Xiao Liu, Chao Ma, Yuting Zou, Yinhe Zheng, Xiaobo Xia, Dawei Jiang, Shaoqing Ren
向阳乔木 · opencode-go/deepseek-v4.1-flash
这篇论文值得看的地方,是它把“玩游戏”当成通用智能体的训练场,而且是从设备级的键盘鼠标轨迹开始学。作者团队阵容不小,Shaoqing Ren、Xiaobo Xia 这些名字在视觉和强化学习圈子里有分量。 但先泼一盆冷水: 摘要里没有交代具体模型规模、训练数据量级、评测胜率数字 ,只说了“comparable to skilled players”和“comp...