@inproceedings{wang-etal-2026-beyond-policy,
    title = "Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning",
    author = "Wang, Yutong  and
      Ji, Ryan  and
      Li, Kaixin  and
      Bi, Baolong  and
      Feng, Tao  and
      Sartoretti, Guillaume Adrien",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2694/",
    pages = "61285--61301",
    ISBN = "979-8-89176-459-0"
}