ByteDance Research has released DAPO (Dynamic Sampling Policy Optimization), an open-source reinforcement learning system for LLMs, aiming to improve reasoning abilities and address reproducibility issues. DAPO includes innovations like Clip-Higher, Dynamic Sampling, Token-level Policy Gradient Loss, and Overlong Reward Shaping, achieving a score of 50 on the AIME 2024 benchmark with the Qwen2.5-32B model.
