CoT
链式思维（Chain of Thought，CoT）是一种用于提升大型语言模型推理能力的提示方法。其核心思想是在生成最终答案之前，引导模型逐步输出中间推理步骤，从而将复杂问题分解为一系列有序的子步骤。该方法广泛应用于数学推理、逻辑推断和多步骤问答等任务，能够显著提高模型在复杂任务上的准确性和可解释性。
Core Facts
Chain-of-Thought (CoT) reasoning was proposed by the Google Brain team in 2022 and improves accuracy on complex tasks by guiding the model to expand its reasoning step by step.
Chain of Thought能显著提升模型在数学推理、逻辑判断等需要多步推导的任务上的表现
Agent planning capabilities are typically implemented through the ReAct (Reasoning + Acting) framework.
Timeline (last 90 days)
The author ignored all CoT (chain-of-thought) models, considering them wasteful of tokens and slower.
In Agent development, CoT often serves as the underlying mechanism of the planning module, helping the model decompose complex goals into executable sub-steps, while ReAct is responsible for interacting with external tools and environments, and the two complement each other.
The core Agent architecture encompasses three core technologies: CoT/ReAct chain-of-thought, RAG retrieval-augmented generation, and model memory mechanisms.
Best practices for getting reliable scores from large models include using a scoring rubric, scoring multiple dimensions separately and then weighting them, calibrating with few-shot examples, requiring chain-of-thought analysis item by item, and optionally using multiple sampling with averaging or setting temperature=0.
ReAct交替进行推理与行动，CoT通过中间步骤提升单步推理质量，ToT通过树状搜索探索多条解题路径
All Facts (9)
Chain-of-Thought (CoT) reasoning was proposed by the Google Brain team in 2022 and improves accuracy on complex tasks by guiding the model to expand its reasoning step by step.
90%VerifiedChain of Thought能显著提升模型在数学推理、逻辑判断等需要多步推导的任务上的表现
90%VerifiedAgent planning capabilities are typically implemented through the ReAct (Reasoning + Acting) framework.
90%VerifiedThe core finding of CoT is that when models are asked to think step by step, accuracy on tasks such as arithmetic and commonsense reasoning improves substantially.
80%UnverifiedThe author ignored all CoT (chain-of-thought) models, considering them wasteful of tokens and slower.
50%UnverifiedIn Agent development, CoT often serves as the underlying mechanism of the planning module, helping the model decompose complex goals into executable sub-steps, while ReAct is responsible for interacting with external tools and environments, and the two complement each other.
50%UnverifiedThe core Agent architecture encompasses three core technologies: CoT/ReAct chain-of-thought, RAG retrieval-augmented generation, and model memory mechanisms.
50%UnverifiedBest practices for getting reliable scores from large models include using a scoring rubric, scoring multiple dimensions separately and then weighting them, calibrating with few-shot examples, requiring chain-of-thought analysis item by item, and optionally using multiple sampling with averaging or setting temperature=0.
50%UnverifiedReAct交替进行推理与行动，CoT通过中间步骤提升单步推理质量，ToT通过树状搜索探索多条解题路径
50%