@article{weaktostronggeneralizationviadirectonpol, title = {Weak-to-Strong Generalization via Direct On-Policy Distillation}, author = {Shiyuan Feng and Huan-ang Gao and Haohan Chi and Hanlin Wu and Zhilong Zhang and Zheng Jiang and Bingxiang He and Wei-Ying Ma and Ya-Qin Zhang and Hao Zhou}, year = {2026}, eprint = {2607.05394}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.05394}, }