DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

@article{Guo2025,
  author = {Guo, Daya and Yang, Damai and Zhang, Hanze and Song, Jiangtao and Zhang, Rujie and Xu, Rundong and He, Yujia},
  journal = {arXiv preprint arXiv:2501.12948},
  title = {DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning},
  year = {2025},
}