@article{bayesianpreferencelearningfortesttimeste,
  title = {Bayesian Preference Learning for Test-Time Steerable Reward Models},
  author = {Jiwoo Hong and Shao Tang and Zhipeng Wang},
  year = {2026},
  eprint = {2602.08819},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.08819},
}