Overview

Multi-agent debate examines whether language models can reason more reliably by proposing answers, sharing evidence, challenging peers, and revising judgments. Common approaches assign roles such as advocate, critic, and judge; use retrieval and structured evidence checks; or adapt who communicates and when debate stops. Researchers apply these methods to mathematics, question answering, fact-checking, and medical or legal decisions, but results vary across tasks and model groups. A central tension is that debate can uncover errors when agents contribute useful independent information, yet consensus can also spread mistakes, suppress dissent, and add substantial cost.

Latest papers

CardsList

154 papers16 papers in the last four weeks, down 11% on the four weeks before. 0.1% of all new papers.

  1. Debate2Create: Robot Co-design via Multi-Agent LLM Debate

    Oct 29, 2025Kevin Qiu, Marek CyganRobot Morphology-Control Co-DesignMulti-Agent Debate

  2. When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

    Oct 23, 2025Yongqiang Chen, Gang Niu, James Cheng +2Multi-Agent DebateMulti-Agent Collaboration

  3. Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate

    Oct 11, 2025Pratik S. Sachdeva, Tom van NuenenLLM Decision-MakingMoral Reasoning in Language Models