mlsanityData to 7 Oct 2026

Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

arXiv 2305.04091 ↗First posted 6 May 2023cs.CLcited by 550

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

Abstract (arXiv)

Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zero-shot-CoT concatenates the target problem statement with "Let's think step by step" as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation errors, missing-step errors, and semantic misunderstanding errors. To address the missing-step errors, we propose Plan-and-Solve (PS) Prompting. It consists of two components: first, devising a plan to divide the entire task into smaller subtasks, and then carrying out the subtasks according to the plan. To address the calculation errors and improve the quality of generated reasoning steps, we extend PS prompting with more detailed instructions and derive PS+ prompting. We evaluate our proposed prompting strategy on ten datasets across three reasoning problems. The experimental results over GPT-3 show that our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem. The code can be found at https://github.com/AGI-Edgerunners/Plan-and-Solve-Prompting.

Key facts. Cited by 550 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 36 of its 53 references that are in the map. First posted on arXiv 6 May 2023.

Builds on

36 of 53 references.

Closest ancestors · 10

Same direction, newest first

  1. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters20 Dec
  2. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning15 Dec
  3. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  4. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct
  5. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  6. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  7. 2022Large Language Models are Zero-Shot Reasoners24 May
  8. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  9. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  10. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 26

  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. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2022Emergent Abilities of Large Language Modelscited by 2,483
  10. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,793
  11. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
14 more
  1. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  2. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
  3. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  4. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  5. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 642
  6. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  7. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  8. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  9. 2023Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agentscited by 396
  10. 2016Solving General Arithmetic Word Problemscited by 353
  11. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  12. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 334
  13. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
  14. 2022Successive Prompting for Decomposing Complex Questionscited by 94

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 68; 2024: 119; 2025: 185; 2026: 178.

550 papers.

Sort:

By area:

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  2. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  3. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  4. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  5. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  6. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  7. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  8. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
  9. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  10. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 420
  11. 2024Understanding the planning of LLM agents: A surveycited by 414
  12. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
38 more
  1. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  2. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 291
  3. 2025DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoningcited by 261
  4. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoningcited by 257
  5. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  6. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  7. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  8. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  9. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  10. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  11. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  12. 2023A Simple LLM Framework for Long-Range Video Question-Answeringcited by 176
  13. 2023An LLM Compiler for Parallel Function Callingcited by 170
  14. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Modelscited by 160
  15. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 130
  16. 2024AutoWebGLM: A Large Language Model-based Web Navigating Agentcited by 130
  17. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 129
  18. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  19. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 108
  20. 2023Question Decomposition Improves the Faithfulness of Model-Generated Reasoningcited by 107
  21. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 107
  22. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  23. 2025Measuring what Matters: Construct Validity in Large Language Model Benchmarkscited by 102
  24. 2024An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMcited by 97
  25. 2023Where Would I Go Next? Large Language Models as Human Mobility Predictorscited by 92
  26. 2023Conversational Health Agents: A Personalized LLM-Powered Agent Frameworkcited by 91
  27. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 89
  28. 2024DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agentscited by 89
  29. 2025GuardReasoner: Towards Reasoning-based LLM Safeguardscited by 89
  30. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Serverscited by 89
  31. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  32. 2024Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunitiescited by 83
  33. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 80
  34. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 76
  35. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  36. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  37. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  38. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72

50 most cited of 550 All 550 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
  2. 2024Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models
  3. 2023Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages
  4. 2024Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns
  5. 2023An automatically discovered chain-of-thought prompt generalizes to novel models and datasets
  6. 2023Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
  7. 2025Zero-Shot Verification-guided Chain of Thoughts
  8. 2024Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods