@inproceedings{wang-etal-2026-aligning,
    title = "Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling",
    author = "Wang, Jiaxuan  and
      Hu, Yulan  and
      Yang, Wenjin  and
      Pan, Zheng  and
      Li, Xin  and
      Guo, Lan-Zhe",
    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.1062/",
    pages = "23174--23200",
    ISBN = "979-8-89176-390-6"
}