mlsanityData to 14 Oct 2026

Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints

arXiv 2509.18382 ↗First posted 22 Sep 2025cs.AIcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Test-time compute scaling has demonstrated the ability to improve the performance of reasoning language models by generating longer chain-of-thought (CoT) sequences. However, this increase in performance comes with a significant increase in computational cost. In this work, we investigate two compute constraint strategies: (1) reasoning length constraint and (2) model quantization, as methods to reduce the compute demand of reasoning models and study their impact on their safety performance. Specifically, we explore two approaches to apply compute constraints to reasoning models: (1) fine-tuning reasoning models using a length controlled policy optimization (LCPO) based reinforcement learning method to satisfy a user-defined CoT reasoning length, and (2) applying quantization to maximize the generation of CoT sequences within a user-defined compute constraint. Furthermore, we study the trade-off between the computational efficiency and the safety of the model.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 17 of its 25 references that are in the map. First posted on arXiv 22 Sep 2025.

Builds on

17 of 25 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025s1: Simple test-time scaling31 Jan
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug

Other references · 15

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  6. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  7. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  8. 2024OpenAI o1 System Cardcited by 1,244
  9. 2024A StrongREJECT for Empty Jailbreakscited by 385
  10. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  11. 2019A Constructive Prediction of the Generalization Error Across Scalescited by 210
  12. 2025SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilitiescited by 136
3 more
  1. 2024Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversationscited by 129
  2. 2024Low-Rank Quantization-Aware Training for LLMscited by 43
  3. 2024The Landscape and Challenges of HPC Research and LLMscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  2. 2025Efficient Reasoning Models: A Survey
  3. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs
  4. 2025Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability
  5. 2026The Art of Efficient Reasoning: Data, Reward, and Optimization
  6. 2025Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought
  7. 2025How Far Are We from Optimal Reasoning Efficiency?
  8. 2026Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning