CLSep 20, 2024

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

arXiv:2409.13449v15 citationsh-index: 24
Originality Incremental advance
AI Analysis

This addresses the problem of high learning costs and iterative difficulties in prompt engineering for non-AI experts, though it appears incremental as it builds on existing prompt optimization principles.

The paper tackles the challenge of non-AI experts struggling to formulate high-quality prompts for LLMs by proposing Minstrel, a multi-agent system that automates structural prompt generation, which significantly enhances LLM performance as shown in experiments and a case study.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes