Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation

Computer Science > Artificial Intelligence [Submitted on 18 Mar 2026] Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation Jianan Chen, Zhifang Zhang, Shuo He, Linan Yue, Lei Feng, Minling Zhang Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper, we reveal that LRMs' safety degradation occurs only after CoT is enabled, and this degradation is not observed when CoT is disabled. This observation motivates us to consider encouraging LRMs to make safety decisions before CoT generation. To this end, we propose a novel safety alignment method that promotes the safety decision-making of LRMs before starting CoT generation. Specifically, we first utilize a Bert-based classifier to extract safety decision signals from a safe model (e.g., a CoT-disabled LRM) and then integrate these signals into LRMs' safety alignment as auxiliary supervision. In this way, the safety gradients can be backpropagated to the LRMs' latent representations, effectively strengthening the LRMs' safety decision-making abilities against CoT generation. Extensive experiments demonstrate that our method substantially improves the safety capabilities of LRMs while effectively maintaining LRMs' general reasoning performance. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.17368 [cs.AI]   (or arXiv:2603.17368v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.17368 Focus to learn more Submission history From: Chen Jianan [view email] [v1] Wed, 18 Mar 2026 05:21:12 UTC (1,733 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)