@inproceedings{zhao-etal-2026-maestro,
    title = "{MAESTRO}: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization",
    author = "Zhao, Yang  and
      Wang, Hepeng  and
      Ding, Xiao  and
      Ouyang, Yangou  and
      Cai, Bibo  and
      Xiong, Kai  and
      Gao, Jinglong  and
      Sun, Zhouhao  and
      Du, Li  and
      Qin, Bing  and
      Liu, Ting",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1019/",
    pages = "22267--22283",
    ISBN = "979-8-89176-390-6"
}