@article{laserlearningtoadaptivelyselectreward, title = {LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits}, author = {Duy Nguyen and Archiki Prasad and Elias Stengel-Eskin and Mohit Bansal}, year = {2024}, eprint = {2410.01735}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.01735v1}, }