mlsanityData to 14 Oct 2026

Exploring the System 1 Thinking Capability of Large Reasoning Models

arXiv 2504.10368 ↗First posted 14 Apr 2025cs.CL cs.AIcited by 10

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

Abstract (arXiv)

This paper explores the system 1 thinking capability of Large Reasoning Models (LRMs), the intuitive ability to respond efficiently with minimal token usage. While existing LRMs rely on long-chain reasoning and excel at complex tasks, their system 1 thinking ability remains largely underexplored. This capability is essential as it reflects models' difficulty awareness and reasoning efficiency, both critical for real-world applications. We propose S1-Bench, a multi-domain, multilingual benchmark comprising model-simple system 1 questions. Our investigation of 28 LRMs reveals under-accuracy and inefficiency on system 1 problems. We find existing efficient reasoning methods either generalize poorly to simple questions or sacrifice performance for efficiency. Further exploration uncovers LRMs' early difficulty awareness accompanied by lower confidence, and shows that problem difficulty is implicitly encoded in hidden states.

Key facts. Cited by 10 papers 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 55 of its 92 references that are in the map. First posted on arXiv 14 Apr 2025.

Builds on

55 of 92 references.

Closest ancestors · 29

Same direction, newest first

  1. 2025Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time12 Apr
  2. 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning10 Apr
  3. 2025Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning6 Apr
  4. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  5. 2025Hawkeye:Efficient Reasoning with Model Collaboration1 Apr
  6. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond27 Mar
  7. 2025InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models9 Mar
  8. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  9. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models6 Mar
  10. 2025Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding3 Mar
  11. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach3 Mar
  12. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning25 Feb
17 more
  1. 2025Dynamic Parallel Tree Search for Efficient LLM Reasoning22 Feb
  2. 2025LightThinker: Thinking Step-by-Step Compression21 Feb
  3. 2025Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking19 Feb
  4. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  5. 2025CoT-Valve: Length-Compressible Chain-of-Thought Tuning13 Feb
  6. 2025Confidence Improves Self-Consistency in LLMs10 Feb
  7. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
  8. 2025s1: Simple test-time scaling31 Jan
  9. 2025Reward-Guided Speculative Decoding for Efficient LLM Reasoning31 Jan
  10. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
  11. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs30 Dec
  12. 2024Efficiently Scaling LLM Reasoning with Certaindex30 Dec
  13. 2024Token-Budget-Aware LLM Reasoning24 Dec
  14. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems12 Dec
  15. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling30 Aug
  16. 2024Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning24 Aug
  17. 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning19 Jan

Other references · 26

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  5. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  6. 2025LIMO: Less is More for Reasoningcited by 498
  7. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  8. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  9. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  10. 2025CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillationcited by 225
  11. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyondcited by 175
  12. 2025SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilitiescited by 136
14 more
  1. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  2. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!cited by 132
  3. 2025Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuningcited by 123
  4. 2025Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingcited by 117
  5. 2023Wider and Deeper LLM Networks are Fairer LLM Evaluatorscited by 94
  6. 2025Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Modelscited by 51
  7. 2025Think When You Need: Self-Adaptive Chain-of-Thought Learningcited by 38
  8. 2025Z1: Efficient Test-time Scaling with Codecited by 35
  9. 2025SOTOPIA-Omega: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agentscited by 16
  10. 2025Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?cited by 15
  11. 2025Reasoning Does Not Necessarily Improve Role-Playing Abilitycited by 14
  12. 2024Distilling Reasoning Ability from Large Language Models with Adaptive Thinkingcited by 13
  13. 2025TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidancecited by 11
  14. 2025DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025Dynamic Early Exit in Reasoning Modelscited by 219
  2. 2025OptimalThinkingBench: Evaluating Over and Underthinking in LLMscited by 35
  3. 2025Adaptive Social Learning via Mode Policy Optimization for Language Agentscited by 15
  4. 2026Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Modelscited by 8
  5. 2025LLM-First Search: Self-Guided Exploration of the Solution Spacecited by 6
  6. 2026Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectoriescited by 4
  7. 2026Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Informationcited by 3
  8. 2025CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Taskscited by 1
  9. 2026SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoningcited by 1
  10. 2026Thinking Inertia: LLMs Keep Thinking When Told Not Tocited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
  2. 2025THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models
  3. 2025Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
  4. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
  5. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
  6. 2025Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
  7. 2025Efficient Inference for Large Reasoning Models: A Survey
  8. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking