@article{grpounifyingthegrpoframeworkswithlearnab, title = {$λ$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences}, author = {Yining Wang and Jinman Zhao and Chuangxin Zhao and Shuhao Guan and Gerald Penn and Shinan Liu}, year = {2025}, eprint = {2510.06870}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.06870}, }