@article{smallerweakeryetbettertrainingllm,
  title = {Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling},
  author = {Hritik Bansal and Arian Hosseini and Rishabh Agarwal and Vinh Q. Tran and Mehran Kazemi},
  year = {2024},
  eprint = {2408.16737},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.16737v2},
}