mlsanityData to 7 Oct 2026

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

arXiv 2602.09341 ↗First posted 10 Feb 2026cs.AIcited by 16

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

also in 1 more
Abstract (arXiv)

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 59 of its 84 references that are in the map. First posted on arXiv 10 Feb 2026.

Builds on

59 of 84 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025MARS: toward more efficient multi-agent collaboration for LLM reasoning24 Sep
  2. 2025Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning4 Sep
  3. 2025ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning12 Mar
  4. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks4 Mar
  5. 2024MALT: Improving Reasoning with Multi-Agent LLM Training2 Dec
  6. 2024AFlow: Automating Agentic Workflow Generation14 Oct
  7. 2024GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion21 Sep
  8. 2023Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration14 Nov

Other references · 51

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023Qwen Technical Reportcited by 3,273
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  12. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
38 more
  1. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
  2. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
  3. 2024RewardBench: Evaluating Reward Models for Language Modelingcited by 480
  4. 2024Automated Design of Agentic Systemscited by 360
  5. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 267
  6. 2023Reward Design with Language Modelscited by 257
  7. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 246
  8. 2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 235
  9. 2023Universal Self-Consistency for Large Language Model Generationcited by 198
  10. 2023Self-Evaluation Guided Beam Search for Reasoningcited by 195
  11. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  12. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  13. 2023Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generationcited by 103
  14. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  15. 2024AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planningcited by 81
  16. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  17. 2024Factual Confidence of LLMs: on Reliability and Robustness of Current Estimatorscited by 59
  18. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systemscited by 58
  19. 2024TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategycited by 47
  20. 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agentscited by 45
  21. 2024Large Language Model-based Human-Agent Collaboration for Complex Task Solvingcited by 38
  22. 2024TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysiscited by 28
  23. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 28
  24. 2024Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Datasetcited by 24
  25. 2025A Survey of Reasoning and Agentic Systems in Time Series with Large Language Modelscited by 21
  26. 2025HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDLcited by 17
  27. 2025VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generationcited by 15
  28. 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Taskscited by 15
  29. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  30. 2025LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generationcited by 13
  31. 2026Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learningcited by 13
  32. 2024On the Limitations of Large Language Models (LLMs): False Attributioncited by 12
  33. 2022PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learningcited by 11
  34. 2025Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learningcited by 10
  35. 2024Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoningcited by 9
  36. 2024Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learningcited by 7
  37. 2025QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?cited by 6
  38. 2025Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Modelcited by 6

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 16.

16 papers.

Sort:

By area:

  1. 2026Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learningcited by 9
  2. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  3. 2026Beyond Consensus: Trace-Level Synthesis in Mixture of Agentscited by 3
  4. 2026ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scalingcited by 2
  5. 2026Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitrationcited by 2
  6. 2026AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditingcited by 1
  7. 2026Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesiscited by 1
  8. 2026AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Compositioncited by 1
  9. 2026MIRROR: Learning from the Other View for Multi-Modal Reasoningcited by 1
  10. 2026BRA-Audit: Budgeted Runtime Auditing for LLM Multi-Agent Systems via Cumulative-Exposure Audit-Point Placementcited by 1
  11. 2026Candidate supply and answer selection shape the value of LLM judging in multi-agent systemscited by 1
  12. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMscited by 0
4 more
  1. 2026RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generationcited by 0
  2. 2026Controlled Decoding Attacks on Black-Box LLMscited by 0
  3. 2026Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systemscited by 0
  4. 2026SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning
  2. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
  3. 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
  4. 2026LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems
  5. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
  6. 2025Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
  7. 2026MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing
  8. 2026Agentic Systems as Boosting Weak Reasoning Models