Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts

TL;DR

This paper introduces Minstrel, a multi-agent system for automated structural prompt generation, which improves LLM performance and usability for non-AI experts by reducing prompt design complexity.

Contribution

It presents Minstrel, a novel multi-agent framework with reflection for generating structured prompts, addressing high learning costs and update difficulties in prompt engineering.

Findings

Structural prompts enhance LLM performance.

Minstrel automates prompt creation effectively.

User survey indicates improved ease of use.

Abstract

LLMs have demonstrated commendable performance across diverse domains. Nevertheless, formulating high-quality prompts to assist them in their work poses a challenge for non-AI experts. Existing research in prompt engineering suggests somewhat scattered optimization principles and designs empirically dependent prompt optimizers. Unfortunately, these endeavors lack a structural design, incurring high learning costs and it is not conducive to the iterative updating of prompts, especially for non-AI experts. Inspired by structured reusable programming languages, we propose LangGPT, a structural prompt design framework. Furthermore, we introduce Minstrel, a multi-generative agent system with reflection to automate the generation of structural prompts. Experiments and the case study illustrate that structural prompts generated by Minstrel or written manually significantly enhance the performance of LLMs. Furthermore, we analyze the ease of use of structural prompts through a user survey in our online community.