# Mixture of agents

**Source:** https://promtable.com/glossary/mixture-of-agents

> Mixture of agents is an inference pattern where multiple specialised LLM agents run in parallel and a router aggregator combines their outputs into a single answer — higher quality than any single agent at higher cost.

---
Mixture of agents is an inference pattern where multiple specialised LLM agents run in parallel and a router aggregator combines their outputs into a single answer — higher quality than any single agent at higher cost.

Mixture of agents (Wang et al., 2024) generalises the model-router idea: instead of routing each query to one model, you send it to N models in parallel and have an aggregator LLM synthesise the best answer from all N. Each layer can be a different model family (Claude, GPT, Gemini, open-weight) so the ensemble draws on different training distributions. Open-source implementations (Together AI's mixture-of-agents, MoA-Lite) ship in 2026. The trade-off: 3-7x cost for ~15-25% quality lift on hard benchmarks. Reserve for high-stakes inference where being right matters more than being cheap.

## When to use

- High-stakes single-shot answers (medical, legal, finance summarisation).
- Hard reasoning benchmarks (MMLU-Pro, GPQA).

## Common mistakes

- Running MoA on every query — cost scales fast.
- Using identical models in the ensemble — diversity is the point.

## Related terms

- [model-router](https://promtable.com/glossary/model-router)
- [agent](https://promtable.com/glossary/agent)
- [reasoning-model](https://promtable.com/glossary/reasoning-model)
- [self-consistency](https://promtable.com/glossary/self-consistency)

## Sources

- [Wang et al. 2024 (arXiv)](https://arxiv.org/abs/2406.04692)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/mixture-of-agents
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/mixture-of-agents".
Contact: info@vibecodingturkey.com.