Multi-Agent Debate

Follow this topic Ask about this topic

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

144 papers19 papers in the last four weeks, up 6% on the four weeks before. 0.1% of all new papers.

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
Jul 2, 2026Arman Ghaffarizadeh, Danyal Mohaddes, Aliakbar Izadkhah +1LLM Agent Evaluation Multi-Agent Debate
Independent Researcher · Machine Learning Department & Heinz College Carnegie Mellon University
Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry
Jul 2, 2026Yuante Li, Yicheng Tao, Kate Zhang +3Probabilistic Forecasting Multi-Agent Debate
School of Computer Science, Carnegie Mellon University · College of Engineering, Carnegie Mellon University
Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning
Jun 28, 2026Dayong Liang, Kaisong Gong, Yi Cai +2Multi-Agent Debate Mixture-of-Experts Models
South China University of Technology · Tianjin University · The Hong Kong Polytechnic University
Minority Sentinel: When to Overturn Majority Voting in Multi-Agent LLM Debates
Jun 28, 2026Chuan He, Zebin Chen, Zhengyi Yang +5Multi-Agent Debate Multi-Agent Consensus
University of New South Wales · Euler AI · Macquarie University
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
Jun 23, 2026Sana Ayromlou, Purvi Sehgal, Pradyumna NarayanaMulti-Agent Debate Agentic RAG
Google
Heterogeneous LLM Debate Under Adversarial Peers: Honest Gains, Replacement Costs, and Resilience
Jun 18, 2026Prashanti Nilayam, Kiran Kumar Ramanna, Prashil Tumbade +1Multi-Agent LLM Systems Adversarial Attacks on LLMs
ServiceNow
Hidden Anchors in Multi-Agent LLM Deliberation
Jun 17, 2026Apurba Pokharel, Ram DantuOpinion Dynamics Multi-Agent Debate
Department of CSE University of North Texas 76207, Denton, TX, USA
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI
Jun 16, 2026Lalit Yadav, Akshaj GurugubelliLLM Hallucination Mitigation Multi-Agent Debate
Independent Researcher, Sunnyvale, CA, USA · Independent Researcher, San Diego, CA, USA
Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition
Jun 16, 2026Alessandro Sottovia, Alessandro Torcinovich, Oswald LanzZero-Shot Learning Multi-Agent Debate
Faculty of Engineering, Free University of Bozen-Bolzano, Bolzano, Italy
Misinformation Propagation in Benign Multi-Agent Systems
Jun 15, 2026Jonas Becker, Jan Philip Wahle, Terry Ruas +1Multi-Agent Debate Misinformation Diffusion
University of Göttingen, Germany · LKA NRW, Germany
From Argument Components to Graphs: A Multi-Agent Debate with Confidence Gating for Argument Relations
Jun 14, 2026Jakub Bąba, Jarosław A. ChudziakRelation Extraction Argument Mining
Faculty of Electronics and Information Technology, Warsaw University of Technology, Poland
Confidence Composition for Multiagent Language Model Systems
Jun 11, 2026Ali Elahi, Michael J. Curry, Barbara Di EugenioMulti-Agent LLM Systems Probability Calibration
University of Illinois Chicago
ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
Jun 11, 2026Fuqiang Niu, Bowen ZhangMulti-Agent Debate Multi-Agent Consensus
School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China · School of Artificial Intelligence, Shenzhen Technology University, Shenzhen, China
Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation
Jun 9, 2026Jakub Masłowski, Jarosław A. ChudziakMulti-Agent Debate Computational Argumentation
Institute of Computer Science, Warsaw University of Technology, Warsaw, Poland
Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate
Jun 9, 2026Ali Keramati, Justin Cheok, Jacob Horne +1LLM Agent Evaluation Multi-Agent Debate
University of California, Irvine
The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge
Jun 9, 2026Ali Keramati, Justin Cheok, Jacob Horne +1LLM Agent Evaluation Multi-Agent Debate
University of California, Irvine
The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment
Jun 7, 2026Xiaoyang Wang, Christopher C. YangLLM Agent Evaluation Multi-Agent Debate
1Drexel University
MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring
Jun 4, 2026Ali Keramati, Shiyuan Zhou, Sharad Mehrotra +1Multi-Agent LLM Systems LLM-as-a-Judge
University of California, Irvine
SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction
Jun 3, 2026Kenfeng Huang, Yi Cai, Xin Wu +2Multi-Agent LLM Systems Multi-Agent Debate
School of Software Engineering, South China University of Technology, Guangzhou, China
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
Jun 2, 2026Sanjay Das, Ran Elgedawy, Ethan Seefried +2Multi-Agent LLM Systems AI Risk Management
Oak Ridge National Laboratory Oak Ridge, Tennessee, USA
Collaborative Disagreement Resolution for Scalable Oversight
Jun 2, 2026Yuyang Jiang, Chacha Chen, Teng Wu +4Scalable Oversight Multi-Agent Debate
Department of Computer Science, University of Chicago, Chicago, IL, USA · Microsoft, Redmond, WA, USA · Department of Biostatistics and Bioinformatics, Duke University, Durham, NC, USA +1
The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation
Jun 2, 2026Herun Wan, Jiaying Wu, Minnan Luo +4Multi-Agent LLM Systems LLM Agent Evaluation
Xi’an Jiaotong University · National University of Singapore · Yunnan University +1
When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning
Jun 1, 2026Chirag Parmar, Akshat Mehta, Henglin Wu +2Multi-Agent Debate
1Meta Platforms, Inc.
Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
Jun 1, 2026Wanshuang Gou, Zihan LiuMulti-Agent LLM Systems Multi-Agent System Optimization
Chengdu University
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
May 31, 2026Blaž Bertalanič, Carolina FortunaMulti-Agent LLM Systems Multi-Agent Debate
Jozef Stefan Institute
FinCom: A Financial Multi-Agent Demo with Disagree-or-Commit Deliberation
May 31, 2026Chao Peter Yang, Zixiao Tan, Kaisen Yao +3LLM Sycophancy LLM Agent Orchestration
Duke University United States · ClearPath United States
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
May 30, 2026Xiqi Hao, Zengqing Wu, Yu-Xuan Qiu +4LLM Agent Evaluation Multi-Agent Debate
Beijing Institute of Technology, Zhuhai · University of Osaka · Shenzhen University
Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market Resolution
May 29, 2026Tarun KotaMulti-Agent LLM Systems Multi-Agent Debate
Yale University
Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model Debate
May 28, 2026Tom PecherLLM Evaluation Hallucination in Language Models
Department of Computer Science University of Bath
Detection Without Correction: A Two-Parameter Decomposition of Multi-Stage LLM Pipelines
May 26, 2026Prashanti Nilayam, Kiran Ramanna, Prashil TumbadeLLM Self-Correction LLM Evaluation
Servicenow CA, USA

Jul 2, 2026J/K move · Enter open · S save

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates

Arman Ghaffarizadeh, Danyal Mohaddes, Aliakbar Izadkhah, Shahriar Noroozizadeh

Independent Researcher · Machine Learning Department & Heinz College Carnegie Mellon University

LLM Agent Evaluation Multi-Agent Debate LLM Agents Multi-Agent Systems

Open paper AskPDF arXiv

LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly to say. We study whether such social structure, without any explicit objective in the prompt, changes what an agent expresses publicly relative to an off-the-record (OTR) channel elicited under the same condition. We introduce a dual-channel debate framework in which agents produce public utterances that enter the shared history alongside OTR responses that are recorded but never shown to the other participant. Across 10 models, 3 scenarios, and 5 variations within each scenario, alignment-inducing settings produce systematic public-OTR divergence in the targeted agent, with its decision divergence rising from a

\sim

3% baseline to roughly 40%. The effect is consistent across four aggregate analyses: stance, semantic similarity, natural language inference, and survey responses. In some cases, the OTR response explicitly attributes public accommodation to relational pressures, such as career risk or sponsorship obligation. The findings suggest that agent evaluation should extend beyond explicit goals and detect emergent objectives. We present a dual-channel evaluation framework and complementary behavioral measures that operationalize this assessment.