按年被提到
20242024 · 1 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2406.04692 · cs.CL

Mixture-of-Agents Enhances Large Language Model Capabilities

Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, James Zou · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-06-16 · 最近 2025-02-12
2不同的人
2活跃月份
2讨论串
126被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Recent advances in large language models (LLMs) demonstrate substantial capabilities in natural language understanding and generation tasks. With the growing number of LLMs, how to harness the collective expertise of multiple LLMs is an exciting open direction. Toward this goal, we propose a new approach that leverages the collective strengths of multiple LLMs through a Mixture-of-Agents (MoA) methodology. In our approach, we construct a layered MoA architecture wherein each layer comprises multiple LLM agents. Each agent takes all the outputs from agents in the previous layer as auxiliary information in generating its response. MoA models achieves state-of-art performance on AlpacaEval 2.0, MT-Bench and FLASK, surpassing GPT-4 Omni. For example, our MoA using only open-source LLMs is the leader of AlpacaEval 2.0 by a substantial gap, achieving a score of 65.1% compared to 57.5% by GPT-4 Omni.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论p1esk · 2024-06

“we achieved a margin of 7.6% Are you one of the original contributors of the work done at together.ai [1], or are you trying to take credit for it? [1] https://arxiv.org/abs/2406.04692”

Ask HN: Multiple LLM work together to give higher than gpt4o performance原评论 ↗
被提交为 story · 1 次