mlsanityData to 14 Oct 2026

OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation

arXiv 2506.02397 ↗First posted 3 Jun 2025cs.AIcited by 17

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

Abstract (arXiv)

Human cognition operates through two complementary modes: fast intuitive thinking and slow deliberate thinking. Vanilla large language models (LLMs) predominantly follow the fast-thinking paradigm, producing immediate responses; while recent large reasoning models (LRMs) adopt slow-thinking strategies, generating detailed reasoning chains before arriving at answers. While LRMs often achieve higher accuracy, this comes at the cost of substantially increased token usage. To address this efficiency-accuracy trade-off, we propose OThink-R1, a hybrid reasoning framework that integrates both modes within a single LRM and enables automatic mode switching based on problem characteristics. We first identify three major patterns of essential and redundant reasoning trajectories in LRMs, which guide the design of an auxiliary LLM-based judge that adaptively determines when slow thinking is necessary. Leveraging the judge's decisions, we construct a hybrid fine-tuning dataset by pruning redundant reasoning to produce fast-thinking samples and retaining complete reasoning for slow-thinking samples. This dataset is then used to fine-tune LRMs, equipping them with inherent autonomous mode-selection capabilities. Extensive experiments on mathematical and question-answering benchmarks show that OThink-R1 reduces reasoning token usage significantly while maintaining competitive accuracy. The code is available at https://github.com/AgenticIR-Lab/OThink-R1.

Key facts. Cited by 17 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 42 of its 55 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

42 of 55 references.

Closest ancestors · 24

Same direction, newest first

  1. 2025CP-Router: An Uncertainty-Aware Router Between LLM and LRM26 May
  2. 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning22 May
  3. 2025ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning30 Apr
  4. 2025Dynamic Early Exit in Reasoning Models22 Apr
  5. 2025Reasoning Models Can Be Effective Without Thinking14 Apr
  6. 2025Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?9 Apr
  7. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning2 Apr
  8. 2025Effectively Controlling Reasoning Models through Thinking Intervention31 Mar
  9. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond27 Mar
  10. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning6 Mar
  11. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models6 Mar
  12. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach3 Mar
12 more
  1. 2025Reasoning with Latent Thoughts: On the Power of Looped Transformers24 Feb
  2. 2025TokenSkip: Controllable Chain-of-Thought Compression in LLMs17 Feb
  3. 2025CoT-Valve: Length-Compressible Chain-of-Thought Tuning13 Feb
  4. 2025The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks12 Feb
  5. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
  6. 2025Efficient Reasoning with Hidden Thinking31 Jan
  7. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning22 Jan
  8. 2024Token-Budget-Aware LLM Reasoning24 Dec
  9. 2024Compressed Chain of Thought: Efficient Reasoning Through Dense Representations17 Dec
  10. 2024C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness16 Dec
  11. 2024What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective31 Oct
  12. 2024Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces13 Oct

Other references · 18

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  4. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  5. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  6. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
  7. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  8. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 318
  9. 2025Chain of Draft: Thinking Faster by Writing Lesscited by 297
  10. 2025Training Language Models to Reason Efficientlycited by 247
  11. 2024Distilling System 2 into System 1cited by 159
  12. 2025Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuningcited by 123
6 more
  1. 2025SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMscited by 116
  2. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 94
  3. 2024The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Modelscited by 63
  4. 2024Factual Confidence of LLMs: on Reliability and Robustness of Current Estimatorscited by 61
  5. 2024Can Language Models Learn to Skip Steps?cited by 59
  6. 2025Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalizationcited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 8.

17 papers.

Sort:

  1. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  2. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Surveycited by 18
  3. 2025ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shapingcited by 17
  4. 2026Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learningcited by 13
  5. 2026Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Modelscited by 8
  6. 2025Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysiscited by 6
  7. 2025PEAR: Phase Entropy Aware Reward for Efficient Reasoningcited by 5
  8. 2025Overthinking Reduction with Decoupled Rewards and Curriculum Data Schedulingcited by 4
  9. 2026Efficient Reasoning with Balanced Thinkingcited by 4
  10. 2025VideoPro: Adaptive Program Reasoning for Long Video Understandingcited by 3
  11. 2026Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoningcited by 3
  12. 2025SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuningcited by 2
5 more
  1. 2025MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detectioncited by 0
  2. 2026Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learningcited by 0
  3. 2026Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correctioncited by 0
  4. 2026HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMscited by 0
  5. 2026DyCon: Dynamic Reasoning Control via Evolving Difficulty Modelingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Controlling Thinking Speed in Reasoning Models
  2. 2025A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law
  3. 2026Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
  4. 2024DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models
  5. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
  6. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
  7. 2025Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
  8. 2025Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time