@misc{kumar2025post,
  title={LLM Post-Training: A Deep Dive into Reasoning Large Language Models},
  author={Komal Kumar and Tajamul Ashraf and Omkar Thawakar and Rao Muhammad Anwer and Hisham Cholakkal and Mubarak Shah and Ming-Hsuan Yang and Phillip H. S. Torr and Salman Khan and Fahad Shahbaz Khan},
  year={2025},
  eprint={2502.21321},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2502.21321}
}