MACM：利用多智能体系统进行条件挖掘以解决复杂数学问题
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
AI总结：
本文提出多智能体条件挖掘系统（MACM）提示方法，通过多智能体协作解决复杂数学问题并提升泛化能力，使 GPT-4 Turbo 在 MATH 数据集五级问题上的准确率从 54.68% 提升至 76.73%。
摘要：
近期，诸如 GPT-4 等大型语言模型的进展在处理标准查询方面展现了卓越能力。尽管取得了这些进展，它们在需要复杂、多步逻辑推理的高级数学问题上的表现却显著下降。为了增强其推理能力，当前的研究深入探索了提示工程，以 Tree of Thought 和 Graph of Thought 等方法为代表。然而，这些现有方法面临两大显著局限。首先，它们在解决复杂数学问题上的有效性受到一定限制。其次，需要为每个问题设计不同提示的要求阻碍了其泛化能力。针对这些局限，本文提出了多智能体条件挖掘系统（MACM）提示方法。它不仅解决了复杂数学问题，还在各种数学语境中展现出强大的泛化能力。在 MACM 的辅助下，GPT-4 Turbo 在 MATH 数据集中最具挑战性的五级数学问题上的准确率从 54.68% 提升至 76.73%。代码可在 https://github.com/bin123apple/MACM 获取。
英文摘要：
Recent advancements in large language models, such as GPT-4, have demonstrated remarkable capabilities in processing standard queries. Despite these advancements, their performance substantially declines in \textbf{advanced mathematical problems requiring complex, multi-step logical reasoning}. To enhance their inferential capabilities, current research has delved into \textit{prompting engineering}, exemplified by methodologies such as the Tree of Thought and Graph of Thought. Nonetheless, these existing approaches encounter two significant limitations. Firstly, their effectiveness in tackling complex mathematical problems is somewhat constrained. Secondly, the necessity to design distinct prompts for individual problems hampers their generalizability. In response to these limitations, this paper introduces the \textit{Multi-Agent System for conditional Mining} (\textbf{MACM}) prompting method. It not only resolves intricate mathematical problems but also demonstrates strong generalization capabilities across various mathematical contexts. With the assistance of MACM, the accuracy of GPT-4 Turbo on the most challenging level five mathematical problems in the MATH dataset increase from $\mathbf{54.68\%} \text{ to } \mathbf{76.73\%}$. The code is available in \url{https://github.com/bin123apple/MACM}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
