NOTE: This site has just upgraded to Forester 5.x and is still having some style and functionality issues, we will fix them ASAP.

reference. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning [guo2025deepseek]
✍️source

  • 2025
  • Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, others
@article{guo2025deepseek,
 title = {Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning},
 author = {Guo, Daya and Yang, Dejian and Zhang, Haowei and Song, Junxiao and Zhang, Ruoyu and Xu, Runxin and Zhu, Qihao and Ma, Shirong and Wang, Peiyi and Bi, Xiao and others},
 year = {2025},
 journal = {arXiv preprint arXiv:2501.12948}
}