← 返回论文库

Self-Refine: Iterative Refinement with Self-Feedback

Madaan, et al. (CMU) · 2023

L3.1 · LLM Agent Patterns & FrameworksNeurIPS 2023#reasoning#self-improvement

CORE IDEA

三步循环：initial output → critique（同一 LLM）→ refine，无需训练纯 prompting。

L-ANCHOR · 为什么在这一层重要

自我修正最简范式

arXiv:2303.17651 ↗

相关论文

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Graph of Thoughts: Solving Elaborate Problems with Large Language Models