# SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards

**Published:** November 6, 2026
**Author:** Yichen Sun, Qirui Liu, Yan Wang, Jianan Lin, Linbo Jiang, Shiyu Wang, Zhibo Wang, Zhixuan Chu
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/saver-2-reasoning-based-safety-alignment-for-large-reasoning-models-via

arXiv:2611.07482v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have achieved impressive performance via explicit Chain-of-Thought (CoT) reasoning, yet this process introduces critical safety risks. We formalize LRM safety objectives as requiring non-malicious…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2611.07482)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*