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.
@article{arxiv.2409.13449,
title = {Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts},
author = {Ming Wang and Yuanzhong Liu and Xiaoyu Liang and Yijie Huang and Daling Wang and Xiaocui Yang and Sijia Shen and Shi Feng and Xiaoming Zhang and Chaofeng Guan and Yifei Zhang},
journal= {arXiv preprint arXiv:2409.13449},
year = {2024}
}
Comments
arXiv admin note: text overlap with arXiv:2402.16929