Safety in Large Reasoning Models: A Survey

Cheng Wang, Yue Liu, Baolong Bi, Duzhen Zhang, Zhong-Zhi Li +7 more
4/24/2025
cs.CL

No official code found. Best implementation: WangCheng0116/Awesome-LRMs-Safety (90 stars, last commit 2025-08-25).

Abstract

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their vulnerabilities and safety have arisen, which can pose challenges to their deployment and application in real-world settings. This paper presents a comprehensive survey of LRMs, meticulously exploring and summarizing the newly emerged safety risks, attacks, and defense strategies. By organizing these elements into a detailed taxonomy, this work aims to offer a clear and structured understanding of the current safety landscape of LRMs, facilitating future research and development to enhance the security and reliability of these powerful models.

View on arXivView PDF

Code Implementations(1)

WangCheng0116/Awesome-LRMs-SafetyCommunity68%

Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning Models to enhance their security and reliability.

903Apr 24, 20251 years ago

Similar Papers

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

89% match1 repo302025

SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models

89% match2025

ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models

88% match1 repo272025

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

87% match1 repo672025

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models

86% match2025

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model

86% match1 repo72025

Cite this paper

@article{wang2025safety,
  title  = {Safety in Large Reasoning Models: A Survey},
  author = {Cheng Wang and Yue Liu and Baolong Bi and Duzhen Zhang and Zhong-Zhi Li and Yingwei Ma and Yufei He and Shengju Yu and Xinfeng Li and Junfeng Fang and Jiaheng Zhang and Bryan Hooi},
  year   = {2025},
  eprint = {2504.17704},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.17704v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.17704.svg)](https://codeofpaper.com/paper/2504.17704)

Discussion