Alibaba Introduces Group Sequence Policy Optimization (GSPO): An Efficient Reinforcement Learning Algorithm that Powers the Qwen3 Models

Alibaba Introduces Group Sequence Policy Optimization (GSPO): An Efficient Reinforcement Learning Algorithm that Powers the Qwen3 Models

Reinforcement learning (RL) plays a crucial role in scaling language models, enabling them to solve complex tasks such as competition-level mathematics and programming through deeper reasoning. However, achieving stable and reliable training dynamics is a challenge when scaling RL with larger computational resources. Current state-of-the-art algorithms, such as GRPO, struggle with serious stability issues during the training of gigantic language…