@article{reinforcementlearningvsdistillation,
  title = {Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning},
  author = {Minwu Kim and Anubhav Shrestha and Safal Shrestha and Aadim Nepal and Keith Ross},
  year = {2025},
  eprint = {2505.14216},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.14216v1},
}