@inproceedings{fang-etal-2026-allocate,
    title = "How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization",
    author = "Fang, Yangyi  and
      Lin, Jiaye  and
      Fu, Xiaoliang  and
      Qin, Cong  and
      Shi, Haolin  and
      Hu, Chaowen  and
      Pan, Lu  and
      Zeng, Ke  and
      Cai, Xunliang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.724/",
    pages = "14727--14744",
    ISBN = "979-8-89176-395-1"
}