字节 Seed：Research PapersDeyao Zhu, Xin Zhou, Shengling Qin, Xuekai Zhu, Hangliang Ding, Shu Zhong, Zixin Wen, Zhonglin Xie, Chenhui Gou, Linxuan Ren, Yueyang Wang, Junfeng Zhong, Rui Liu, Tian Gao, Yangguang Lin, Jingyuan Zhang, Maojia Song, Xuan Qi, Jinhong Wu, Chenyang Zhang, Yinzhu Piao, Ziru Niu, Hongbin Lin, Lingxiang Meng, Peng Tang, Chengyao Tang, Shanyu Wu, Huanyu Zheng, Yu Liu, Liya Zhu, He Wang, Ming Ding, Ziyu Wan, Hao Liu, Sibo Wang, Haotian Zhu, Xintian Zhang, Nan Chai, Yipeng Liu, Panhao Lai, Sihang Yuan, Zixin Su, Ge Zhang, Wangchunshu Zhou, Yantao Du, Wenhao Huang, Guang Shi2026-07-06 00:007 月 6 日
EdgeBench：从真实世界环境中揭示学习缩放定律
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
AI 导读字节跳动Seed团队发布EdgeBench，包含134个真实世界任务，覆盖科学发现、软件工程等6个领域，每任务支持至少12小时连续智能体运行。基于约38,000小时交互数据，发现总体性能与环境交互时间呈精确对数S形缩放定律（R²=0.998），且智能体学习速度约每三个月翻倍。已公开51个任务及完整评估框架。
另有 1 家信源报道
来源：字节 Seed：Research Papers · arxiv.org