Definition

Chain-of-Thought

Chain-of-thought prompting asks the model to reason step by step before answering, in its simplest form by appending "Let's think step by step." Because tokens are generated sequentially, the intermediate reasoning becomes context for the final answer, effectively a scratchpad. Accuracy on math and logic problems can jump 20 to 40 percent with no model change. Reasoning models later built this behavior into training.