mlsanityData to 14 Oct 2026

Think When You Need: Self-Adaptive Chain-of-Thought Learning

arXiv 2504.03234 ↗First posted 4 Apr 2025cs.CL cs.AI cs.LGcited by 38

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Chain of Thought (CoT) reasoning enhances language models' performance but often leads to inefficient "overthinking" on simple problems. We identify that existing approaches directly penalizing reasoning length fail to account for varying problem complexity. Our approach constructs rewards through length and quality comparisons, guided by theoretical assumptions that jointly enhance solution correctness with conciseness. Moreover, we further demonstrate our method to fuzzy tasks where ground truth is unavailable. Experiments across multiple reasoning benchmarks demonstrate that our method maintains accuracy while generating significantly more concise explanations, effectively teaching models to "think when needed."

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 12 of its 16 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

12 of 16 references.

References · 12

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  5. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  6. 2024OpenAI o1 System Cardcited by 1,244
  7. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  8. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  9. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 384
  10. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruningcited by 279
  11. 2025PairJudge RM: Perform Best-of-N Sampling with Knockout Tournamentcited by 22
  12. 2025Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoningcited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 22; 2026: 16.

38 papers.

Sort:

By area:

  1. 2025Efficient Reasoning Models: A Surveycited by 95
  2. 2025R-KV: Redundancy-aware KV Cache Compression for Reasoning Modelscited by 54
  3. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  4. 2025R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Searchcited by 30
  5. 2025A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Modelscited by 25
  6. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficientcited by 24
  7. 2025Towards Concise and Adaptive Thinking in Large Reasoning Models: A Surveycited by 18
  8. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Modelscited by 17
  9. 2025Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Modelcited by 14
  10. 2025Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoningcited by 13
  11. 2025Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Modelscited by 11
  12. 2025LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimizationcited by 11
26 more
  1. 2025Exploring the System 1 Thinking Capability of Large Reasoning Modelscited by 10
  2. 2025Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Timecited by 10
  3. 2025How Far Are We from Optimal Reasoning Efficiency?cited by 8
  4. 2025Probing the Difficulty Perception Mechanism of Large Language Modelscited by 8
  5. 2026Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Modelscited by 8
  6. 2026VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoningcited by 8
  7. 2025Efficient Long CoT Reasoning in Small Language Modelscited by 6
  8. 2025Enhancing Large Language Models through Structured Reasoningcited by 5
  9. 2025TokenSqueeze: Performance-Preserving Compression for Reasoning LLMscited by 5
  10. 2026Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoningcited by 4
  11. 2026Efficient Reasoning with Balanced Thinkingcited by 4
  12. 2025Verifying Meta-Awareness via Predictive Rewards in Reasoning Modelscited by 3
  13. 2026ESTAR: Early-Stopping Token-Aware Reasoning For Efficient Inferencecited by 3
  14. 2025Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoningcited by 2
  15. 2026Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillationcited by 2
  16. 2025SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scalingcited by 1
  17. 2026RANKVIDEO: Reasoning Reranking for Text-to-Video Retrievalcited by 1
  18. 2026Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoningcited by 1
  19. 2026Ada-RS: Adaptive Rejection Sampling for Selective Thinkingcited by 1
  20. 2026TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Modelscited by 1
  21. 2026STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimescited by 1
  22. 2026Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generationcited by 1
  23. 2026SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoningcited by 1
  24. 2026ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoningcited by 1
  25. 2026MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controllercited by 0
  26. 2026Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
  2. 2025From Reasoning to Super-Intelligence: A Search-Theoretic Perspective
  3. 2024Rethinking Chain-of-Thought from the Perspective of Self-Training
  4. 2025SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
  5. 2024A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning
  6. 2026Latent Reasoning with Supervised Thinking States
  7. 2025Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
  8. 2024Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought