**DAPO: An Open-Source RL System from ByteDance Seed and Tsinghua Air**

> An Open-source RL System from ByteDance Seed and Tsinghua AIR - BytedTsinghua-SIA/DAPO DAPO: an Open-source RL System from ByteDance Seed and Tsinghua AIR Important 🔥 News!!! \[2025/05\] We update the wandb training record of full DAPO and the checkpoint which achieved 50%+ on AIME 2024. We also provide instructions for evaluation on AIME 2024. \[2025/03\] We release the training record of an early version of DAPO (w/o...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-21 07:19（北京时间）
- **原文**：[打开原文](https://github.com/BytedTsinghua-SIA/DAPO)