mlsanityData to 7 Oct 2026

Chain of Thoughtlessness? An Analysis of CoT in Planning

arXiv 2405.04776 ↗First posted 8 May 2024cs.AIcited by 100

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

Abstract (arXiv)

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution procedures-with the intuition that it is possible to in-context teach an LLM an algorithm for solving the problem. This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain, and examines the performance of two state-of-the-art LLMs across two axes: generality of examples given in prompt, and complexity of problems queried with each prompt. While our problems are very simple, we only find meaningful performance improvements from chain of thought prompts when those prompts are exceedingly specific to their problem class, and that those improvements quickly deteriorate as the size n of the query-specified stack grows past the size of stacks shown in the examples. We also create scalable variants of three domains commonly studied in previous CoT papers and demonstrate the existence of similar failure modes. Our results hint that, contrary to previous claims in the literature, CoT's performance improvements do not stem from the model learning general algorithmic procedures via demonstrations but depend on carefully engineering highly problem specific prompts. This spotlights drawbacks of chain of thought, especially the sharp tradeoff between possible performance gains and the amount of human labor necessary to generate examples with correct reasoning traces.

Key facts. Cited by 100 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 42 of its 57 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

42 of 57 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting21 Mar
  2. 2024How Interpretable are Reasoning Explanations from Prompting Large Language Models?19 Feb
  3. 2024Demystifying Chains, Trees, and Graphs of Thoughts25 Jan
  4. 2023Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting20 Jul
  5. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Prompting10 Jun
  6. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective24 May
  7. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting7 May
  8. 2023Faithful Chain-of-Thought Reasoning31 Jan
  9. 2022Reasoning with Language Model Prompting: A Survey19 Dec
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct
  11. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  12. 2022Large Language Models are Zero-Shot Reasoners24 May
3 more
  1. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 27

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  5. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  6. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  9. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  10. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  11. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  12. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
15 more
  1. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
  2. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  3. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  4. 2021A Diverse Corpus for Evaluating and Developing English Math Word Problem Solverscited by 314
  5. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  6. 2022Exploring Length Generalization in Large Language Modelscited by 204
  7. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Taskscited by 137
  8. 2022Faithful Reasoning Using Large Language Modelscited by 130
  9. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 122
  10. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 111
  11. 2022Limitations of Language Models in Arithmetic and Symbolic Inductioncited by 71
  12. 2023A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoningcited by 41
  13. 2024Efficient Tool Use with Chain-of-Abstraction Reasoningcited by 33
  14. 2023KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrievalcited by 10
  15. 2024Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategiescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 57; 2026: 27.

100 papers.

Sort:

By area:

  1. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  2. 2025TRAIL: Trace Reasoning and Agentic Issue Localizationcited by 98
  3. 2024Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planningcited by 95
  4. 2025Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Modelscited by 94
  5. 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBenchcited by 93
  6. 2025Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoningcited by 89
  7. 2025The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMscited by 62
  8. 2025SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planningcited by 58
  9. 2025Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verificationcited by 49
  10. 2025Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lenscited by 42
  11. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  12. 2025LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelscited by 38
38 more
  1. 2025Large Language Models for Planning: A Comprehensive and Systematic Surveycited by 38
  2. 2024Robust Planning with LLM-Modulo Framework: Case Study in Travel Planningcited by 34
  3. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environmentscited by 32
  4. 2025The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learningcited by 30
  5. 2025Limitations of Large Language Models in Clinical Problem-Solving Arising from Inflexible Reasoningcited by 29
  6. 2025Entropy-based Exploration Conduction for Multi-step Reasoningcited by 28
  7. 2024Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoningcited by 27
  8. 2025FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoningcited by 25
  9. 2025Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluationcited by 20
  10. 2024Exploring and Benchmarking the Planning Capabilities of Large Language Modelscited by 19
  11. 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Codecited by 18
  12. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agentscited by 18
  13. 2024Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1cited by 17
  14. 2024On the Limit of Language Models as Planning Formalizerscited by 17
  15. 2025A Survey on Large Language Models for Automated Planningcited by 17
  16. 2024A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoningcited by 15
  17. 2025Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planningcited by 15
  18. 2026FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insightscited by 13
  19. 2025ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Modelcited by 11
  20. 2025LLM+AL: Bridging Large Language Models and Action Languages for Complex Reasoning about Actionscited by 10
  21. 2025Climplicit: Climatic Implicit Embeddings for Global Ecological Taskscited by 9
  22. 2025From Reasoning to Super-Intelligence: A Search-Theoretic Perspectivecited by 9
  23. 2024Robust Planning with Compound LLM Architectures: An LLM-Modulo Approachcited by 8
  24. 2025Agentic Workflows for Conversational Human-AI Interaction Designcited by 8
  25. 2025Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillationcited by 8
  26. 2026Symphony: A Cognitively-Inspired Multi-Agent System for Long-Video Understandingcited by 8
  27. 2024Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorercited by 7
  28. 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learningcited by 7
  29. 2025Enhancing LLM Planning Capabilities through Intrinsic Self-Critiquecited by 7
  30. 2025On Learning Verifiers and Implications to Chain-of-Thought Reasoningcited by 6
  31. 2025When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI Taskscited by 6
  32. 2025Frontier Large Language Models Rival State-of-the-Art Plannerscited by 6
  33. 2025ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planningcited by 5
  34. 2025Position: We Need An Algorithmic Understanding of Generative AIcited by 5
  35. 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Datacited by 5
  36. 2025ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoningcited by 5
  37. 2026Geometry-Calibrated Conformal Abstention for Language Modelscited by 5
  38. 2025GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analyticscited by 4

50 most cited of 100 All 100 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
  2. 2025Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
  3. 2025The Challenge of Teaching Reasoning to LLMs Without RL or Distillation
  4. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  5. 2026The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
  6. 2026Soft Guidance Starts to Outperform CoT Prompting as LLMs Improve
  7. 2026How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
  8. 2023Stress Testing Chain-of-Thought Prompting for Large Language Models