@inproceedings{qi-etal-2026-stapo,
    title = "{STAPO}: Selective Trajectory-Aware Policy Optimization for {LLM} Agent Training",
    author = "Qi, Qiuyi  and
      Liang, Tian  and
      Bao, Mutian  and
      Zhang, Jinjian  and
      Liu, Dongnan  and
      Zhou, Wei  and
      Mo, Linjian  and
      Kong, Ming  and
      Liu, Jie  and
      Zhang, Feng  and
      Zhu, Qiang",
    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.1308/",
    pages = "28371--28392",
    ISBN = "979-8-89176-390-6"
}