@article{
qu2026pope,
title={{POPE}: Learning to Reason on Hard Problems via Privileged On-Policy Exploration},
author={Yuxiao Qu and Amrith Setlur and Virginia Smith and Ruslan Salakhutdinov and Aviral Kumar},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=pbyIoUW7YV},
note={J2C Certification}
}