Chain-of-Thought Prompting

Chain-of-Thought Prompting is a Few-Shot Prompting technique where model is given examples of step-by-step reasoning rather than standard question and answer examples, encouraging the model to think through a problem before returning an answer.

A technique for eliciting LLM Reasoning, which can also support Planning in Agentic Reasoning systems.

Described in paper Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.