ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments

ArXi:2508.04204v2 Announce Type: replace-cross Large Reasoning Models (LRMs) have nstrated 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.