Self-Reflection in LLM Agents: Effects on Problem-Solving Performance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Renze, Matthew, Guven, Erhan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909536900612096
author Renze, Matthew
Guven, Erhan
author_facet Renze, Matthew
Guven, Erhan
contents 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. All code and data are available on GitHub at https://github.com/matthewrenze/self-reflection
format Preprint
id arxiv_https___arxiv_org_abs_2405_06682
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
Renze, Matthew
Guven, Erhan
Computation and Language
Artificial Intelligence
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. All code and data are available on GitHub at https://github.com/matthewrenze/self-reflection
title Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.06682