AI Agent Architecture — ReAct, Memory, Planning and Multi-Agent Systems · Reasoning — How an LLM Thinks Before Acting
Tree of Thoughts — Exploring Multiple Reasoning Paths
Reasoning — How an LLM Thinks Before Acting
Introduction
Yao et al. (2023) proposed Tree of Thoughts (ToT) as a generalization of Chain-of-Thought: instead of a single linear reasoning chain, the model explores a tree of possible reasoning paths, evaluates them, and selects the most promising. This lesson describes the ToT architecture, the role of "thought states", evaluation and selection mechanisms, and key differences from CoT and self-consistency.