1
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
探讨SFT如何优化自身并为强化学习做准备，揭示大模型训练策略的关键演进方向
arXiv:2602.01058v2 Announce Type: replace-cross Abstract: Post-training of reasoning LLMs is a holistic process that typically consists of an offline …