Mixture-of-Agents
Also called MoA.
Mixture-of-Agents (MoA) arranges language models in layers, where each model receives all outputs from the previous layer as auxiliary input and an aggregator synthesizes a final response.
Description
Wang et al. reported that a mixture of open models outperformed a single strong proprietary model on an instruction-following benchmark.
Sources
- Wang et al. (2024). Mixture-of-Agents Enhances Large Language Model Capabilities.
Cite this entry
Protologue. (2026). Mixture-of-Agents. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0052). https://protologue.com/t/mixture-of-agents/
BibTeX
@misc{protologue_mixture_of_agents,
title = {Mixture-of-Agents},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0052},
url = {https://protologue.com/t/mixture-of-agents/}
}