mlsanityData to 7 Oct 2026

Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

arXiv 2309.15402 ↗First posted 27 Sep 2023cs.CL cs.AIcited by 184

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

Abstract (arXiv)

Reasoning, a fundamental cognitive process integral to human intelligence, has garnered substantial interest within artificial intelligence. Notably, recent studies have revealed that chain-of-thought prompting significantly enhances LLM's reasoning capabilities, which attracts widespread attention from both academics and industry. In this paper, we systematically investigate relevant research, summarizing advanced methods through a meticulous taxonomy that offers novel perspectives. Moreover, we delve into the current frontiers and delineate the challenges and future directions, thereby shedding light on future research. Furthermore, we engage in a discussion about open questions. We hope this paper serves as an introduction for beginners and fosters future research. Resources have been made publicly available at https://github.com/zchuz/CoT-Reasoning-Survey

Key facts. Cited by 184 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 148 of its 252 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

148 of 252 references.

Closest ancestors · 31

Same direction, newest first

  1. 2023CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought20 Sep
  2. 2023Chain-of-Thought Reasoning is a Policy Improvement Operator15 Sep
  3. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering25 Aug
  4. 2023Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought16 Aug
  5. 2023Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals11 Aug
  6. 2023Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions25 Jul
  7. 2023Measuring Faithfulness in Chain-of-Thought Reasoning17 Jul
  8. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step24 Jun
  9. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Prompting10 Jun
  10. 2023Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning30 May
  11. 2023Tab-CoT: Zero-shot Tabular Chain of Thought28 May
  12. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective24 May
19 more
  1. 2023Better Zero-Shot Reasoning with Self-Adaptive Prompting23 May
  2. 2023The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning23 May
  3. 2023Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling17 May
  4. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models6 May
  5. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework5 May
  6. 2023SCOTT: Self-Consistent Chain-of-Thought Distillation3 May
  7. 2023Why think step by step? Reasoning emerges from the locality of experience7 Apr
  8. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data24 Feb
  9. 2022Large Language Models Are Reasoning Teachers20 Dec
  10. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters20 Dec
  11. 2022Reasoning with Language Model Prompting: A Survey19 Dec
  12. 2022Teaching Small Language Models to Reason16 Dec
  13. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  14. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct
  15. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  16. 2022Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango16 Sep
  17. 2022Large Language Models are Zero-Shot Reasoners24 May
  18. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  19. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thought16 Mar

Other references · 117

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  9. 2023Let's Verify Step by Stepcited by 3,598
  10. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  12. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
38 more
  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  3. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,114
  4. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  5. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  6. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  8. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  9. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  10. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  11. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  12. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  13. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  14. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  15. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  16. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  17. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 975
  18. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  19. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  20. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  21. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  22. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  23. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  24. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  25. 2021NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actionscited by 735
  26. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 710
  27. 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Modelscited by 694
  28. 2022Large Language Models Can Self-Improvecited by 656
  29. 2019MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalismscited by 653
  30. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  31. 2022Contrastive Decoding: Open-ended Text Generation as Optimizationcited by 598
  32. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  33. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  34. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  35. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
  36. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  37. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 511
  38. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 504

50 most cited of 117 All 117 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 75; 2025: 75; 2026: 22.

184 papers.

Sort:

By area:

  1. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 446
  2. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 362
  3. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 258
  4. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  5. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  6. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  7. 2025SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMscited by 110
  8. 2024Jailbreak Vision Language Models via Bi-Modal Adversarial Promptcited by 103
  9. 2024OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Drivingcited by 93
  10. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Surveycited by 82
  11. 2024Self-playing Adversarial Language Game Enhances LLM Reasoningcited by 80
  12. 2024Agent-E: From Autonomous Web Navigation to Foundational Design Principles in Agentic Systemscited by 79
38 more
  1. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  2. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  3. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluationscited by 66
  4. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  5. 2024Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learningcited by 63
  6. 2025Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Modelscited by 61
  7. 2025Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Modelcited by 60
  8. 2024Visual Agents as Fast and Slow Thinkerscited by 53
  9. 2023Contrastive Chain-of-Thought Promptingcited by 52
  10. 2025Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendationcited by 50
  11. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  12. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detectioncited by 46
  13. 2025Open Deep Search: Democratizing Search with Open-source Reasoning Agentscited by 46
  14. 2024Puzzle Solving using Reasoning of Large Language Models: A Surveycited by 44
  15. 2024When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignmentcited by 43
  16. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  17. 2023TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Modelscited by 39
  18. 2024LLM-Powered User Simulator for Recommender Systemcited by 38
  19. 2024ACPBench: Reasoning about Action, Change, and Planningcited by 37
  20. 2025Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Modelscited by 37
  21. 2023The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysiscited by 34
  22. 2024How Likely Do LLMs with CoT Mimic Human Reasoning?cited by 34
  23. 2025VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Searchcited by 34
  24. 2025Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Explorationcited by 33
  25. 2025MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Modelscited by 33
  26. 2024LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environmentscited by 31
  27. 2024How Much Can RAG Help the Reasoning of LLM?cited by 31
  28. 2025Contextual Integrity in LLMs via Reasoning and Reinforcement Learningcited by 30
  29. 2025ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviewscited by 28
  30. 2024Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recencycited by 27
  31. 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?cited by 27
  32. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methodscited by 27
  33. 2024Planning with Multi-Constraints via Collaborative Language Agentscited by 26
  34. 2024Instance-adaptive Zero-shot Chain-of-Thought Promptingcited by 25
  35. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 24
  36. 2024MECD: Unlocking Multi-Event Causal Discovery in Video Reasoningcited by 23
  37. 2025Ontology Generation using Large Language Modelscited by 23
  38. 2023Using Large Language Models for Qualitative Analysis can Introduce Serious Biascited by 22

50 most cited of 184 All 184 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Towards Better Chain-of-Thought Prompting Strategies: A Survey
  2. 2023Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  4. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  5. 2026When does Chain-of-Thought Help: A Markovian Perspective
  6. 2024Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
  7. 2026The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
  8. 2025Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought