@inproceedings{xu-etal-2026-beyond-grpo,
    title = "Beyond {GRPO} and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training",
    author = "Xu, Yuanda  and
      Sang, Hejian  and
      Zhou, Zhengze  and
      He, Ran  and
      Wang, Zhipeng  and
      Geramifard, Alborz",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.639/",
    pages = "13392--13408",
    ISBN = "979-8-89176-462-0"
}