SOD: Step-wise On-policy Distillation for Small Language Model Agents 文章

ArXiv CS.CL2026-08-04PAPERen作者: Qiyong Zhong, Mao Zheng, Mingyang Song, Xin Lin, Jie Sun, Houcheng Jiang, Xiang Wang, Junfeng Fang

SOD: Step-wise On-policy Distillation for Small Language Model Agents · 相关人物

暂无数据