MARS：一個融合蘇格拉底式引導的多智能體框架，用於自動化提示優化

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

大型語言模型的基本問答格式涉及輸入提示並接收回應，而提示的品質直接影響回應的有效性。自動提示優化（APO）旨在擺脫手動設計提示的認知偏見，探索更廣泛的提示設計空間。然而，現有的APO方法存在固定模板靈活性有限和提示空間搜索效率低下的關鍵問題。為此，我們提出了一種融合蘇格拉底指導的多代理框架（MARS），該框架利用多代理融合技術進行自動規劃，並逐步持續優化和評估。具體而言，MARS由七個具有不同功能的代理組成，這些代理自主使用規劃器設計確保靈活性的優化路徑。此外，它採用教師-評論家-學生的蘇格拉底對話模式，在進行有效搜索的同時迭代優化提示。我們在各種數據集上進行了廣泛的實驗，以驗證我們方法的有效性，並進行了額外的分析實驗，以評估模型的進步以及可解釋性。

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.