作者位次 #4/10ICLR 2026Poster· Reinforcement Learning / Everything Else
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
Yuqian Fu · Tinghong Chen · Jiajun Chai · Xihuai Wang · Songjun Tu · Guojun Yin · Shuai Chen · Qichao Zhang · Yuanheng Zhu · Dongbin Zhao