Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
混合代理 (MoA) – 在 AlpacaEval 和 OSS 模型上为 65.1%
Mixture of Agents (MoA) is a novel approach that leverages the collective strengths of multiple LLMs to enhance performance, achieving state-of-the-art results. By employing a layered architecture where each layer comprises several LLM agents, MoA significantly outperforms GPT-4 Omni’s 57.5% on AlpacaEval 2.0 with a score of 65.1%, using only open-source models!
代理混合 (MoA) 是一种新颖的方法，它利用多个 LLMs 的集体优势来增强性能，实现最先进的结果。通过采用每层包含多个 LLM 代理的分层架构，MoA 在 AlpacaEval 2.0 上的表现显着优于 GPT-4 Omni 的 57.5%，得分为 65.1%（仅使用开源模型）！