← 返回论文库

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Besta, et al. (ETH Zurich) · 2023
L3.1 · LLM Agent Patterns & FrameworksAAAI 2024#reasoning
CORE IDEA
ToT 的 generalization：任意 DAG 的 thought 拓扑（合并/分支/反馈）。
L-ANCHOR · 为什么在这一层重要
reasoning 拓扑的最一般形式
arXiv:2308.09687 ↗

相关论文

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
L3.12022
Self-Consistency Improves Chain of Thought Reasoning in Language Models
L3.12022
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
L3.12023
LATS: Language Agent Tree Search Unifies Reasoning, Acting, and Planning
L3.12023