mlsanityData to 7 Oct 2026

Chain of Draft: Thinking Faster by Writing Less

arXiv 2502.18600 ↗First posted 25 Feb 2025cs.CLcited by 290

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

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes verbose, step-by-step reasoning. However, humans typically employ a more efficient strategy: drafting concise intermediate thoughts that capture only essential information. In this work, we propose Chain of Draft (CoD), a novel paradigm inspired by human cognitive processes, where LLMs generate minimalistic yet informative intermediate reasoning outputs while solving tasks. By reducing verbosity and focusing on critical insights, CoD matches or surpasses CoT in accuracy while using as little as only 7.6% of the tokens, significantly reducing cost and latency across various reasoning tasks. Our code and data are available at https://github.com/sileix/chain-of-draft.

Key facts. Cited by 290 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 24 references that are in the map. First posted on arXiv 25 Feb 2025.

Builds on

11 of 24 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models18 Aug
  2. 2023Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought16 Aug
  3. 2022Large Language Models are Zero-Shot Reasoners24 May
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar

Other references · 7

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  6. 2024Concise Thoughts: Impact of Output Length on LLM Reasoning and Costcited by 108
  7. 2024Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategiescited by 44

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 171; 2026: 119.

290 papers.

Sort:

By area:

  1. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2025Dynamic Early Exit in Reasoning Modelscited by 217
  4. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 215
  5. 2025Reasoning Models Can Be Effective Without Thinkingcited by 182
  6. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Modelscited by 154
  7. 2025AdaptThink: Reasoning Models Can Learn When to Thinkcited by 141
  8. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 131
  9. 2025Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingcited by 116
  10. 2025Thinkless: LLM Learns When to Thinkcited by 107
  11. 2025Efficient Reasoning Models: A Surveycited by 93
  12. 2025S-GRPO: Early Exit via Reinforcement Learning in Reasoning Modelscited by 87
38 more
  1. 2025AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learningcited by 86
  2. 2025Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chainscited by 81
  3. 2025Concise Reasoning via Reinforcement Learningcited by 78
  4. 2025Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiencycited by 65
  5. 2025Effectively Controlling Reasoning Models through Thinking Interventioncited by 63
  6. 2025Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RLcited by 59
  7. 2025Efficient Inference for Large Reasoning Models: A Surveycited by 58
  8. 2025PolyMath: Evaluating Mathematical Reasoning in Multilingual Contextscited by 52
  9. 2025AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgetingcited by 50
  10. 2025Inverse Scaling in Test-Time Computecited by 49
  11. 2026CRISP: Compressed Reasoning via Iterative Self-Policy Distillationcited by 49
  12. 2025Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Timecited by 48
  13. 2025SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoningcited by 47
  14. 2025Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasonercited by 38
  15. 2025ARM: Adaptive Reasoning Modelcited by 38
  16. 2025Answer Convergence as a Signal for Early Stopping in Reasoningcited by 38
  17. 2025Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Modelscited by 37
  18. 2025ThinkSwitcher: When to Think Hard, When to Think Fastcited by 37
  19. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 36
  20. 2025Cost-of-Pass: An Economic Framework for Evaluating Language Modelscited by 35
  21. 2025Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoningcited by 34
  22. 2025ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoningcited by 33
  23. 2025Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoningcited by 32
  24. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
  25. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMscited by 31
  26. 2025Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Modelscited by 30
  27. 2025Steering LLM Thinking with Budget Guidancecited by 30
  28. 2025FlashThink: An Early Exit Method For Efficient Reasoningcited by 28
  29. 2025R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routingcited by 28
  30. 2025PixelThink: Towards Efficient Chain-of-Pixel Reasoningcited by 28
  31. 2025Let LRMs Break Free from Overthinking via Self-Braking Tuningcited by 27
  32. 2025AlphaOne: Reasoning Models Thinking Slow and Fast at Test Timecited by 27
  33. 2025Promoting Efficient Reasoning with Verifiable Stepwise Rewardcited by 27
  34. 2025BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokenscited by 27
  35. 2025When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoningcited by 26
  36. 2025Shorten After You're Right: Lazy Length Penalties for Reasoning RLcited by 25
  37. 2025VeriThinker: Learning to Verify Makes Reasoning Model Efficientcited by 24
  38. 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcutscited by 23

50 most cited of 290 All 290 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient Reasoning for LLMs through Speculative Chain-of-Thought
  2. 2024Break the Chain: Large Language Models Can be Shortcut Reasoners
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  4. 2023Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
  5. 2026When Chain-of-Thought Helps and When It Hurts: An Empirical Investigation of the Serial-Depth Bottleneck in LLM Reasoning
  6. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
  7. 2024Self-Harmonized Chain of Thought
  8. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters