@article{reinforcementlearningfrommetaevaluationa,
  title = {Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels},
  author = {Micah Rentschler and Jesse Roberts},
  year = {2026},
  eprint = {2601.21268},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.21268},
}