The step-by-step reasoning a model writes out before its final answer. A 2022 Google paper showed that prompting large models for step-by-step reasoning improves their results on arithmetic, commonsense and symbolic reasoning.
See also
- Reasoning model
A model trained to work through a problem in steps before it answers, spending more test-time compute on problems such as math, coding and analysis.
- Test-time compute
Computation a model spends while answering rather than during training, for example reasoning at length, sampling several answers or searching among them.
- Prompt engineering
Writing and refining prompts to get better and more reliable results from a model, for example by giving clear instructions, examples or a required format.
Cite this term.
CC BY 4.0, attribution required.
Orbyt Labs, Chain of thought (AI Glossary), Oct 18, 2026. https://www.orbytlabs.ai/orbyt-collective/glossary/chain-of-thought
Orbyt Labs Glossaries (Oct 19, 2026), https://www.orbytlabs.ai/glossary#dataset
Last updated .