@article{rethinkingreinforcementfinetuningofllmsa,
  title = {Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective},
  author = {Xiao Hu and Hong Xie and Tao Tan and Defu Lian and Jianyu Han},
  year = {2026},
  eprint = {2601.14599},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.14599},
}