@inproceedings{hernandez2026softmaxgrpo,
  title = {SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation},
  author = {Hernandez, Jefferson and Koo, Jaywon and Xiao, Zilin and Wei, Chen and Ordonez, Vicente},
  year = {2026},
  booktitle = {Confererence on Language Modeling, COLM 2026},
  url = {https://arxiv.org/abs/2608.09271},
}