Reasoning & CoT
15 frameworks — Chain-of-thought methods that guide AI through transparent, step-by-step logical reasoning.
Overview
Chain-of-Thought and related reasoning techniques guide AI through transparent, step-by-step logical processes. By making intermediate thinking visible, these methods dramatically improve accuracy on math, logic, and multi-step problems.
Use reasoning techniques when tasks require more than a simple lookup — when the AI needs to think through a problem, weigh evidence, or build an argument step by step. They range from the simplicity of “Let’s think step by step” to advanced approaches like memory pre-thinking and backward verification.
Reasoning & CoT 15
Chain-of-Thought
2022Encourage step-by-step reasoning through intermediate thinking steps.
Still active techniqueZero-Shot CoT
2022Add “Let’s think step by step” without examples for reasoning tasks.
Still active techniqueAuto-CoT
2022Automatically generate diverse reasoning demonstrations with clustering.
Still active techniqueContrastive CoT
2023Provide both correct and incorrect reasoning examples for contrast.
Still active techniqueStructured CoT
2023Triple-phase reasoning: analysis, structured thinking, summarization.
Still active techniqueFaithful CoT
2023Symbolic reasoning combined with natural language for verifiable answers.
Still active techniqueComplexity-Based
2023Select the most complex reasoning paths for harder problems.
Still active techniqueTab-CoT
2023Tabular format to organize step-by-step reasoning in columns.
Still active techniqueAnalogical Reasoning
2023Solve problems by generating and applying relevant analogies.
Still active techniqueStep-Back Prompting
2023Abstract to higher-level concepts before solving specific problems.
Still active techniqueThread of Thought
2023Segment and reason through lengthy context systematically.
Still active techniqueActive Prompting
2023Identify uncertain examples and annotate them for better demonstrations.
Still active techniqueMemory of Thought
2023Pre-think across unlabeled data before tackling target problems.
Still active techniqueReversing CoT
2023Work backward from conclusions to verify reasoning validity.
Still active techniqueUncertainty-Routed CoT
2023Apply chain-of-thought selectively based on model confidence for cost-optimal reasoning.
Still active techniqueAlgorithm of Thoughts
2024Embed algorithmic search patterns like DFS and BFS directly into prompts for single-call solution-space exploration.
Still active techniqueBuffer of Thoughts
2024Maintain reusable thought-templates from past problem-solving for template-guided reasoning.
Still active techniqueMaieutic Prompting
2022Build recursive explanation trees and use logical consistency to verify commonsense reasoning.
Still active techniqueScratchpad Prompting
2021Show intermediate computation steps in a dedicated workspace before producing final answers.
Still active techniqueSelection-Inference
2023Alternate between selecting relevant premises and drawing conclusions for structured logical reasoning.
Still active techniqueThought Propagation
2023Solve analogous problems first and propagate insights to refine the target problem’s solution.
Still active techniqueChain-of-Symbol
2023Replace natural language with compact symbolic representations for spatial and structural reasoning.
Still active techniqueSymbolic CoT
2023Integrate formal logic rules and symbolic expressions with chain-of-thought for verifiable reasoning.
Still active techniqueDual Process Prompting
2024Route between fast intuitive responses and slow deliberate reasoning based on task complexity.
Still active techniqueChain of Knowledge
2023Generate structured evidence triples with explanation hints for transparent, verifiable reasoning.
Still active techniqueChain of Abstraction
2024Reason with abstract placeholders first, then fill in concrete values using domain tools.
Still active techniqueEverything of Thoughts
2024Combine reinforcement learning and Monte Carlo Tree Search for flexible, efficient reasoning.
Still active techniqueTechnique Comparison
Side-by-side comparison of all 15 frameworks in this category.
| Technique | Year | Best For | Key Strength | Complexity |
|---|---|---|---|---|
| Chain-of-Thought | 2022 | Complex reasoning | Transparent logic | Low |
| Zero-Shot CoT | 2022 | Quick reasoning boost | No examples needed | Very Low |
| Auto-CoT | 2022 | Automated demos | Diversity clustering | Medium |
| Contrastive CoT | 2023 | Error reduction | Contrast learning | Medium |
| Structured CoT | 2023 | Formal reasoning | Three-phase approach | Medium |
| Faithful CoT | 2023 | Verifiable answers | Symbolic + NL | High |
| Complexity-Based | 2023 | Hard problems | Path selection | Medium |
| Tab-CoT | 2023 | Organized reasoning | Tabular format | Low |
| Analogical Reasoning | 2023 | Novel problems | Analogy generation | Medium |
| Step-Back Prompting | 2023 | Abstraction tasks | Concept elevation | Low |
| Thread of Thought | 2023 | Long contexts | Sequential processing | Medium |
| Active Prompting | 2023 | Uncertain examples | Active learning | High |
| Memory of Thought | 2023 | Pre-thinking | Unlabeled data | High |
| Reversing CoT | 2023 | Verification | Backward reasoning | Medium |
| Uncertainty-Routed CoT | 2023 | Cost optimization | Selective reasoning | Medium |
Related Categories
Explore other framework categories that complement Reasoning & CoT.
Decomposition
7 frameworksBreak complex problems into smaller, manageable parts with tree and graph approaches.
Self-Correction
7 frameworksCritique, verify, and iteratively refine AI outputs for better accuracy.
Ensemble Methods
7 frameworksCombine multiple reasoning paths for more reliable results.