MARS：融合苏格拉底式引导的多智能体框架，用于自动化提示优化

MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization

March 21, 2025

作者: Jian Zhang, Zhangqi Wang, Haiping Zhu, Jun Liu, Qika Lin, Erik Cambria

cs.AI

摘要

大型语言模型的基本问答模式涉及输入提示并接收响应，而提示的质量直接影响响应的有效性。自动提示优化（APO）旨在摆脱手动设计提示时的认知偏差，探索更广阔的提示设计空间。然而，现有APO方法存在固定模板灵活性不足及提示空间搜索效率低下等关键问题。为此，我们提出了一种融合苏格拉底引导的多智能体框架（MARS），该框架利用多智能体融合技术进行自动规划，实现逐步持续优化与评估。具体而言，MARS包含七个功能各异的智能体，它们自主运用规划器设计优化路径，确保灵活性。同时，采用教师-批评家-学生的苏格拉底对话模式，在有效搜索的同时迭代优化提示。我们在多个数据集上进行了广泛实验以验证方法的有效性，并通过附加分析实验评估模型的进步性及可解释性。

English

The basic question-answering format of large language models involves inputting a prompt and receiving a response, and the quality of the prompt directly impacts the effectiveness of the response. Automated Prompt Optimization (APO) aims to break free from the cognitive biases of manually designed prompts and explores a broader design space for prompts. However, existing APO methods suffer from limited flexibility of fixed templates and inefficient search in prompt spaces as key issues. To this end, we propose a Multi-Agent framework Incorporating Socratic guidance (MARS), which utilizes multi-agent fusion technology for automatic planning, with gradual continuous optimization and evaluation. Specifically, MARS comprises seven agents, each with distinct functionalities, which autonomously use the Planner to devise an optimization path that ensures flexibility. Additionally, it employs a Teacher-Critic-Student Socratic dialogue pattern to iteratively optimize the prompts while conducting effective search. We conduct extensive experiments on various datasets to validate the effectiveness of our method, and perform additional analytical experiments to assess the model's advancement as well as the interpretability.