多一些智能體就是你所需要的。

More Agents Is All You Need

February 3, 2024

作者: Junyou Li, Qin Zhang, Yangbin Yu, Qiang Fu, Deheng Ye

cs.AI

摘要

我們發現，僅透過採樣和投票方法，大型語言模型（LLMs）的性能隨著實例化代理數量的增加而提升。此方法與現有複雜方法相互獨立，進一步增強LLMs的程度與任務難度相關。我們在廣泛的LLM基準測試中進行了全面實驗，以驗證我們發現的存在，並研究可能促成其發生的特性。我們的程式碼公開可在以下網址找到：https://anonymous.4open.science/r/more_agent_is_all_you_need.

English

We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method is orthogonal to existing complicated methods to further enhance LLMs, while the degree of enhancement is correlated to the task difficulty. We conduct comprehensive experiments on a wide range of LLM benchmarks to verify the presence of our finding, and to study the properties that can facilitate its occurrence. Our code is publicly available at: https://anonymous.4open.science/r/more_agent_is_all_you_need.