Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning 文章

ArXiv CS.CL2026-06-04NEWSen作者: Chongyang He, Rui Zhang, Zixuan Wang, Xin Li
查看原文 →
关系图谱

Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning · 相关技术

相关技术

SFT-then-RL pipelinedifficulty-aware SFT-then-RL frameworkCritique Fine-TuningBridge mechanismRLSFTSmall Language Models