@inproceedings{xu-etal-2026-entropy,
    title = "Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation",
    author = "Xu, Jiacheng  and
      Chen, Feng  and
      Xu, Xiuneng  and
      An, Bo",
    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.2102/",
    pages = "47843--47857",
    ISBN = "979-8-89176-459-0"
}