Tree of Thoughts: Deliberate Problem Solving with Large Language Models

• 类型：arxiv
• 标识：2305.10601
• 链接：https://arxiv.org/abs/2305.10601
• 主题：rag
• 主分类：agent
• 形态：method
• 被引：4726
• 被引来源：Semantic Scholar
• S2被引：4726
• OpenAlex被引：572
• 影响力被引：306
• TLDR：A new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.
• OpenAlex ID：W4377130677
• OpenAlex DOI：10.48550/arxiv.2305.10601
• DOI：10.48550/arxiv.2305.10601
• DOI来源：OpenAlex
• 开放获取：green
• 开放获取链接：https://arxiv.org/pdf/2305.10601
• OpenAlex更新：2026-08-22
• 待LLM分类：否
• 成熟度：research
• 场景：reasoning、problem-solving、tree-search
• 标题中文：Tree of Thoughts：大语言模型的审慎问题求解
• TLDR中文：一种面向语言模型推理的新框架 Tree of Thoughts (ToT)，推广了流行的 Chain of Thought 提示方法，允许在作为问题求解中间步骤的连贯文本单元（thoughts）上进行探索。
• 来源文件：
• [OpenAlex discover]
• [S2 enrich]