AI Agent Architecture — ReAct, Memory, Planning and Multi-Agent Systems · Reasoning — How an LLM Thinks Before Acting
Chain-of-Thought — Why Write Thoughts Before Answering
Reasoning — How an LLM Thinks Before Acting
Introduction
Chain-of-Thought (CoT) is a prompting technique in which the model generates intermediate reasoning steps before giving a final answer. Wei et al. (2022) showed that a few sentences of "thinking aloud" dramatically improves performance on arithmetic, logical, and symbolic tasks — without any changes to model weights. This lesson explains the mechanism behind CoT, the conditions under which it yields gains, and how to apply it correctly in practice.