mlsanityData to 7 Oct 2026

Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning

arXiv 2609.33974 ↗First posted 27 Sep 2026cs.CLcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Large Language Model (LLM) based Multi-Agent Debate (MAD) is one of the most effective test time scaling techniques. Through multi-round communication, agents complement each other in knowledge and reasoning and solve tasks that no single member can solve. However, existing MAD frameworks fail to beat strong Single Agent and Consistency-based baselines under the same strict cost limit, which shakes the foundation of the MAD field. We propose Conditional Progressive Pruning (CPP), a lightweight pruning framework that fully exploits multi-round MAD. CPP outperforms all existing MAD frameworks on multiple dominated benchmarks. It is also the first to fully outperform consistency methods. Our code, detailed agent interaction records will be released soon.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 24 of its 27 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

24 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?24 Aug
  2. 2025MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems5 Mar
  3. 2025S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency7 Feb

Other references · 21

  1. 2025Qwen3 Technical Reportcited by 8,195
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  6. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  9. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  10. 2024More Agents Is All You Needcited by 174
  11. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 162
  12. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
9 more
  1. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  2. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  3. 2024Language Agents as Optimizable Graphscited by 81
  4. 2025Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generationcited by 57
  5. 2024Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Modelscited by 47
  6. 2025AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Predictioncited by 25
  7. 2026OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Modelscited by 12
  8. 2024An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routingcited by 7
  9. 2025MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
  2. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
  3. 2026HCP-MAD:Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
  4. 2025Free-MAD: Consensus-Free Multi-Agent Debate
  5. 2026ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
  6. 2025When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
  7. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
  8. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs