Author: Matthew Renze
Published: 2024-05-05

Summary
Large-language model agents can reflect on their chain of thought to improve problem-solving performance.

Abstract
In this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrectly answered question, we instructed eight types of self-reflecting LLM agents to reflect on their mistakes and provide themselves with guidance to improve problem-solving. Then, using this guidance, each self-reflecting agent attempted to re-answer the same questions. Our results indicate that LLM agents are able to significantly improve their problem-solving performance through self-reflection (p<0.001). In addition, we compared the various types of self-reflection to determine their individual contribution to performance.

Resources

This paper was published in the FLLM 2024 conference proceedings.