arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.07076cs.CL
收藏

关于大语言模型讨论的探讨:智能体的对称性与提示词的相互作用

On the Discussion of Large Language Models: Symmetry of Agents and Interplay with Prompts

College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);CSE, HKUST(香港科技大学计算机科学与工程系)

Qineng Wang, Zihao Wang, Ying Su, Yangqiu Song

AI总结:

本文从智能体对称性角度论证多智能体讨论机制,并实验证明精心设计的提示工程可接近复杂多智能体性能,同时提出基于征服与合并的可扩展讨论机制。

摘要:

已有两种方式被讨论用于解锁大语言模型的推理能力。第一种是提示工程,第二种是结合大语言模型的多次推理,即多智能体讨论。理论上,本文从智能体的对称性角度论证了多智能体讨论机制。实证上,本文报告了提示词与讨论机制相互作用的实验结果,揭示了通过精心设计的提示工程可以接近复杂多智能体机制的经验性最新性能。本文还提出了一种基于征服与合并的可扩展讨论机制,提供了一种使用简单提示词但达到最新性能的简单多智能体讨论解决方案。

英文摘要:

Two ways has been discussed to unlock the reasoning capability of a large language model. The first one is prompt engineering and the second one is to combine the multiple inferences of large language models, or the multi-agent discussion. Theoretically, this paper justifies the multi-agent discussion mechanisms from the symmetry of agents. Empirically, this paper reports the empirical results of the interplay of prompts and discussion mechanisms, revealing the empirical state-of-the-art performance of complex multi-agent mechanisms can be approached by carefully developed prompt engineering. This paper also proposes a scalable discussion mechanism based on conquer and merge, providing a simple multi-agent discussion solution with simple prompts but state-of-the-art performance.

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。

↑