@misc{havrilla2024teaching,
  title={Teaching Large Language Models to Reason with Reinforcement Learning},
  author={Alex Havrilla and Yuqing Du and Sharath Chandra Raparthy and Christoforos Nalmpantis and Jane Dwivedi-Yu and Maksym Zhuravinskyi and Eric Hambro and Sainbayar Sukhbaatar and Roberta Raileanu},
  year={2024},
  eprint={2403.04642},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2403.04642}
}