@article{proxyrewardinternalizationandmechanistic,
  title = {Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization},
  author = {Mohammad Beigi and Ming Jin and Lifu Huang},
  year = {2026},
  eprint = {2606.09711},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.09711},
}