@inproceedings{shi-etal-2026-r3l,
    title = "{R}$^3${L}: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification",
    author = "Shi, Weijie  and
      Chen, Yanxi  and
      Li, Zexi  and
      Pan, Xuchen  and
      Sun, Yuchang  and
      Xu, Jiajie  and
      Zhou, Xiaofang  and
      Li, Yaliang",
    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.1420/",
    pages = "32415--32447",
    ISBN = "979-8-89176-459-0"
}