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.
View on arXiv@article{zhang2025_2503.16874,
title={ MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization },
author={ Jian Zhang and Zhangqi Wang and Haiping Zhu and Jun Liu and Qika Lin and Erik Cambria },
journal={arXiv preprint arXiv:2503.16874},
year={ 2025 }
}