AIBullishSynced Review · Apr 247/105
🧠
Can GRPO be 10x Efficient? Kwai AI’s SRPO Suggests Yes with SRPO
Kwai AI has developed SRPO, a new reinforcement learning framework that reduces LLM post-training steps by 90% while achieving performance comparable to DeepSeek-R1 in mathematics and coding tasks. The two-stage approach with history resampling addresses efficiency limitations in existing GRPO methods.