@article{policyiterationwithhumanfeedbackbringing,
  title = {Policy Iteration with Human Feedback: Bringing Post-Training RL to In-context Learning},
  author = {Minh-Ha Nguyen and Cathy Shyr},
  year = {2026},
  eprint = {2608.16831},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.16831},
}