# Red Teaming Large Reasoning Models

arXiv: https://arxiv.org/abs/2512.00412 · HTML: https://mlsanity.com/paper/2512.00412/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 39 of its 64 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 39)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities](https://mlsanity.com/paper/2502.12025/) (2025)
- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey](https://mlsanity.com/paper/2402.09283/) (2024)
- [Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable](https://mlsanity.com/paper/2503.00555/) (2025)
- [SycEval: Evaluating LLM Sycophancy](https://mlsanity.com/paper/2502.08177/) (2025)
- [Evil Geniuses: Delving into the Safety of LLM-based Agents](https://mlsanity.com/paper/2311.11855/) (2023)
- [H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking](https://mlsanity.com/paper/2502.12893/) (2025)
- [Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities](https://mlsanity.com/paper/2308.12833/) (2023)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [Trading Inference-Time Compute for Adversarial Robustness](https://mlsanity.com/paper/2501.18841/) (2025)
- [AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents](https://mlsanity.com/paper/2409.09013/) (2024)
- [SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models](https://mlsanity.com/paper/2504.08813/) (2025)
- [Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models](https://mlsanity.com/paper/2503.01781/) (2025)
- [MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments](https://mlsanity.com/paper/2506.01616/) (2025)
- [SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning](https://mlsanity.com/paper/2505.16186/) (2025)
- [How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study](https://mlsanity.com/paper/2505.15404/) (2025)
- [Excessive Reasoning Attack on Reasoning LLMs](https://mlsanity.com/paper/2506.14374/) (2025)
- [See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses](https://mlsanity.com/paper/2408.08978/) (2024)
- [When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models](https://mlsanity.com/paper/2504.02010/) (2025)
- [Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level](https://mlsanity.com/paper/2410.06809/) (2024)
- [POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization](https://mlsanity.com/paper/2508.19277/) (2025)

## Built on by (most cited first, 2 of 2)

- [Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization](https://mlsanity.com/paper/2604.07165/) (2026)
- [STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems](https://mlsanity.com/paper/2604.07100/) (2026)

## Abstract (arXiv)

Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains of thought (CoT). However, these models introduce novel safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies, which are not fully captured by existing evaluation methods. To address this gap, we propose RT-LRM, a unified benchmark designed to assess the trustworthiness of LRMs. RT-LRM evaluates three core dimensions: truthfulness, safety and efficiency. Beyond metric-based evaluation, we further introduce the training paradigm as a key analytical perspective to investigate the systematic impact of different training strategies on model trustworthiness. We achieve this by designing a curated suite of 30 reasoning tasks from an observational standpoint. We conduct extensive experiments on 26 models and identify several valuable insights into the trustworthiness of LRMs. For example, LRMs generally face trustworthiness challenges and tend to be more fragile than Large Language Models (LLMs) when encountering reasoning-induced risks. These findings uncover previously underexplored vulnerabilities and highlight the need for more targeted evaluations. In addition, we release a scalable toolbox for standardized trustworthiness research to support future advancements in this important field. Our code and datasets will be open-sourced.