@inproceedings{shi-etal-2026-reinforcement,
    title = "Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models",
    author = "Shi, Dan  and
      Han, Zhuowen  and
      Ostermann, Simon  and
      Jin, Renren  and
      Van Genabith, Josef  and
      Xiong, Deyi",
    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.1808/",
    pages = "38979--39000",
    ISBN = "979-8-89176-390-6"
}