@article{rewardgatedonpolicydistillation, title = {Reward-Gated On-Policy Distillation}, author = {Mohammad Sadegh Akhondzadeh and Vijay Lingam and Atula Tejaswi and Chanakya Ekbote and Sujay Sanghavi and Aleksandar Bojchevski}, year = {2026}, eprint = {2607.04037}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.04037}, }