protologue

Multi-Agent Debate

Also called LLM debate, society of minds.

Multi-agent debate has several model instances propose answers, read each other's reasoning, and revise their answers over multiple rounds until they converge.

Description

Du et al. found that debate improved mathematical reasoning and factual accuracy over single-model answers.

Sources

  1. Du et al. (2023). Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Cite this entry

Protologue. (2026). Multi-Agent Debate. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0051). https://protologue.com/t/multi-agent-debate/

BibTeX
@misc{protologue_multi_agent_debate,
  title = {Multi-Agent Debate},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
  note = {Entry PTL-0051},
  url = {https://protologue.com/t/multi-agent-debate/}
}

Markdown JSON