@inproceedings{wang-etal-2026-reasoningguard,
    title = "{R}easoning{G}uard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments",
    author = "Wang, Yuquan  and
      Zhang, Mi  and
      Wang, Yining  and
      Hong, Geng  and
      Wen, Mi  and
      You, Xiaoyu  and
      Yang, Min",
    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.1453/",
    pages = "31497--31526",
    ISBN = "979-8-89176-390-6",
    abstract = "Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content generation, particularly in the mid-to-late steps of their reasoning processes. Current defense methods, however, depend on costly fine-tuning and additional expert knowledge, which limits their scalability.In this work, we propose ***ReasoningGuard***, an inference-time safeguard for LRMs.It injects timely *safety aha moments* during the reasoning process to guide the model towards harmless yet helpful reasoning.Our approach leverages the internal attention mechanisms of the LRM to accurately identify key points in the reasoning path, triggering safety-oriented reflections.To safeguard both the subsequent reasoning steps and the final answers, we implement a scaling sampling strategy during decoding to select the optimal reasoning path.With minimal additional inference cost, *ReasoningGuard* effectively mitigates four types of jailbreak attacks, including recent ones targeting the reasoning process of LRMs. Our approach outperforms nine existing safeguards, providing state-of-the-art defenses while avoiding common exaggerated safety issues."
}