@inproceedings{li-etal-2026-forge,
    title = "Forge: Quality-Aware Reinforcement Learning for {NP}-Hard Optimization in {LLM}s",
    author = "Li, Xiaozhe  and
      Fang, Xinyu  and
      Ding, Shengyuan  and
      Li, Yang  and
      Li, Linyang  and
      Duan, Haodong  and
      Liu, Qingwen  and
      Chen, Kai",
    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.1413/",
    pages = "28351--28368",
    ISBN = "979-8-89176-395-1"
}