@inproceedings{hu-etal-2026-towards,
    title = "Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures",
    author = "Hu, Yi  and
      Gu, Jiaqi  and
      Wang, Ruxin  and
      Yao, Zijun  and
      Peng, Hao  and
      Wu, Xiaobao  and
      Chen, Jianhui  and
      Zhang, Muhan  and
      Pan, Liangming",
    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.889/",
    pages = "19449--19466",
    ISBN = "979-8-89176-390-6",
    abstract = "Reinforcement learning (RL) has catalyzed the emergence of Large Reasoning Models (LRMs) that have pushed reasoning capabilities to new heights. While their performance has garnered significant excitement, exploring the internal mechanisms driving these behaviors has become an equally critical research frontier. This paper provides a comprehensive survey of the mechanistic understanding of LRMs, organizing recent findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors. By synthesizing these insights, we aim to bridge the gap between black-box performance and mechanistic transparency. Finally, we discuss under-explored challenges to outline a roadmap for future mechanistic studies, including the need for applied interpretability, improved methodologies, and a unified theoretical framework."
}