@article{learningwithasinglerolloutviamontecarlop, title = {Learning with a Single Rollout via Monte Carlo Pass@k Critic}, author = {Fengdi Che and Yang Liu and Lei Yu and Meng Cao and Tong Che and Rupam Mahmood and Dale Schuurmans}, year = {2026}, eprint = {2606.25451}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.25451}, }