@article{reinforcementlearningforreasoninginsmall,
  title = {Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't},
  author = {Quy-Anh Dang and Chris Ngo},
  year = {2025},
  eprint = {2503.16219},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.16219v1},
}