mlsanityData to 7 Oct 2026

Voting or Consensus? Decision-Making in Multi-Agent Debate

arXiv 2502.19130 ↗First posted 26 Feb 2025cs.MA cs.AI cs.CLcited by 55

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic comparison of decision protocols is difficult because many studies alter multiple discussion parameters beyond the protocol. So far, it has been largely unknown how decision-making influences different tasks. This work systematically evaluates the impact of seven decision protocols (e.g., majority voting, unanimity consensus). We change only one variable at a time - the decision protocol - to analyze how different methods affect the collaboration between agents and measure differences in knowledge and reasoning tasks. Our results show that voting protocols improve performance by 13.2% in reasoning tasks and consensus protocols by 2.8% in knowledge tasks compared to other decision protocols. Increasing the number of agents improves performance, while more discussion rounds before voting reduce it. To improve decision-making by increasing answer diversity, we propose two new methods, All-Agents Drafting (AAD) and Collective Improvement (CI). Our methods improve task performance by up to 3.3% with AAD and up to 7.4% with CI. This work demonstrates the importance of decision-making in multi-agent debates beyond scaling.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 28 of its 47 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

28 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 27

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  7. 2024Qwen2 Technical Reportcited by 2,076
  8. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,758
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  10. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
  11. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  12. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
15 more
  1. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  2. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMscited by 297
  3. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  4. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 229
  5. 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoningcited by 195
  6. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?cited by 153
  7. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 140
  8. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 115
  9. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  10. 2017Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Taggingcited by 71
  11. 2024Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Taskscited by 28
  12. 2024Multi-Agent Large Language Models for Conversational Task-Solvingcited by 24
  13. 2021Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detectioncited by 17
  14. 2024CiteAssist: A System for Automated Preprint Citation and BibTeX Generationcited by 11
  15. 2023Designing Digital Voting Systems for Citizens: Achieving Fairness and Legitimacy in Participatory Budgetingcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 37.

55 papers.

Sort:

By area:

  1. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?cited by 74
  2. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoningcited by 27
  3. 2025Literature Review Of Multi-Agent Debate For Problem-Solvingcited by 15
  4. 2025MALLM: Multi-Agent Large Language Models Frameworkcited by 15
  5. 2025Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Taskscited by 11
  6. 2025From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoningcited by 10
  7. 2025MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMscited by 9
  8. 2025Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Studycited by 8
  9. 2025Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarkscited by 8
  10. 2026The Fragility Of Moral Judgment In Large Language Modelscited by 8
  11. 2025Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaborationcited by 6
  12. 2025SPaRC: A Spatial Pathfinding Reasoning Challengecited by 5
38 more
  1. 2025Emergent Bias and Fairness in Multi-Agent Decision Systemscited by 5
  2. 2026ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generationcited by 5
  3. 2026When Is Collective Intelligence a Lottery? Multi-Agent Scaling Laws for Memetic Drift in LLMscited by 5
  4. 2025MAPS: Multi-Agent Personality Shaping for Collaborative Reasoningcited by 4
  5. 2026ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memorycited by 4
  6. 2025A Knowledge-driven Adaptive Collaboration of LLMs for Enhancing Medical Decision-makingcited by 3
  7. 2026AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Taskscited by 3
  8. 2026The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Sizecited by 3
  9. 2026When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent Systemscited by 3
  10. 2025A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMscited by 2
  11. 2026Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrievalcited by 2
  12. 2026Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energycited by 2
  13. 2026Cognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI Frictioncited by 2
  14. 2026OrgAgent: Organize Your Multi-Agent System like a Companycited by 2
  15. 2026EMS: Multi-Agent Voting via Efficient Majority-then-Stoppingcited by 2
  16. 2026Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectivescited by 2
  17. 2026Misinformation Propagation in Benign Multi-Agent Systemscited by 2
  18. 2026Emergence of Biased Consensus in Multi-Agent LLM Debatescited by 2
  19. 2026Flag Game: A Toy Model for Mechanistic Swarm Interpretabilitycited by 2
  20. 2025A Role-Aware Multi-Agent Framework for Financial Education Question Answering with LLMscited by 1
  21. 2025Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Taskscited by 1
  22. 2025RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Designcited by 1
  23. 2026Multiperspectivity as a Resource for Narrative Similarity Predictioncited by 1
  24. 2026Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gymcited by 1
  25. 2026Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted Oncited by 1
  26. 2026What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systemscited by 1
  27. 2026Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidencecited by 1
  28. 2026The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberationcited by 1
  29. 2026A Technical Taxonomy of LLM Agent Communication Protocolscited by 1
  30. 2026Secure and Energy-Efficient Wireless Agentic AI Networkscited by 0
  31. 2026Empirical Cumulative Distribution Function Clustering for LLM-based Agent System Analysiscited by 0
  32. 2026MIND: Multi-agent inference for negotiation dialogue in travel planningcited by 0
  33. 2026One Panel Does Not Fit All: Case-Adaptive Multi-Agent Deliberation for Clinical Predictioncited by 0
  34. 2026Multi-agent decision making: A Blackwell's informativeness approachcited by 0
  35. 2026AgentPSO: Evolving Agent Reasoning Skill via Multi-agent Particle Swarm Optimizationcited by 0
  36. 2026Voting Protocols as Coordination Mechanisms for Role-Constrained Multi-Agent Tutoring Systemscited by 0
  37. 2026L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoningcited by 0
  38. 2026Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agentscited by 0

50 most cited of 55 All 55 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026The impact of multi-agent debate protocols on debate quality: a controlled case study
  2. 2025Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
  3. 2026When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning
  4. 2026The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
  5. 2025When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
  6. 2026Demystifying Multi-Agent Debate: The Role of Confidence and Diversity
  7. 2025Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
  8. 2026Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges