@article{besta2026rpeg, author={Maciej Besta and Leonard Schmidt and Pierre Pang and Patrik Okanovic and Robert Gerstenberger and Torsten Hoefler}, title={{RPEG: Training Reasoning Language Models Scalably and Cost-Effectively}}, journal={arXiv:2611.09207}, year={2026}, month={Nov.}, doi={10.48550/arXiv.2611.09207}, }