@article{reinforcementlearningoutperformssupervis,
  title = {Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering},
  author = {Gang Li and Jizhong Liu and Heinrich Dinkel and Yadong Niu and Junbo Zhang and Jian Luan},
  year = {2025},
  eprint = {2503.11197},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.11197v4},
}