@article{rlisneitherapanaceanoramirageunderstandi,
  title = {RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs},
  author = {Hangzhan Jin and Sicheng Lv and Sifan Wu and Mohammad Hamdaqa},
  year = {2025},
  eprint = {2508.16546},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.16546},
}