---
title: README
emoji: 🏢
colorFrom: indigo
colorTo: indigo
sdk: static
pinned: false
---

# Parallel-R1: Towards Parallel Thinking via Reinforcement Learning 

Tong Zheng, Hongming Zhang, Wenhao Yu, Xiaoyang Wang, Runpeng Dai, Rui Liu, Huiwen Bao, Chengsong Huang, Heng Huang, Dong Yu 

Tencent AI Lab · University of Maryland, College Park · University of North Carolina at Chapel Hill· City University of Hong Kong · Washington University in St. Louis 

---

[cite_start]**[Paper]** [https://arxiv.org/abs/2509.07980](https://arxiv.org/abs/2509.07980)

[cite_start]**[Code]** [https://github.com/zhengkid/Parallel-R1](https://github.com/zhengkid/Parallel-R1)

[cite_start]**[Data & Models]** [https://huggingface.co/Parallel-R1](https://huggingface.co/Parallel-R1)


![Parallel-R1框架图](./framework.jpg)