@article{reinforcementlearningbasedknowledgedisti,
  title = {Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge},
  author = {Yiyang Shen and Lifu Tu and Weiran Wang},
  year = {2026},
  eprint = {2604.02621},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.02621},
}