@article{enhancingreinforcementlearningfinetuning,
  title = {Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner},
  author = {Hao Ma and Zhiqiang Pu and Yang Liu and Xiaolin Ai},
  year = {2026},
  eprint = {2603.18088},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.18088},
}