@article{greedysamplingisprovablyefficientforrlhf, title = {Greedy Sampling Is Provably Efficient for RLHF}, author = {Di Wu and Chengshuai Shi and Jing Yang and Cong Shen}, year = {2025}, eprint = {2510.24700}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.24700}, }