Multi-Agent Reasoning

Follow this topic Ask about this topic

Multi-agent reasoning examines how AI agents combine knowledge and perspectives to solve problems that may exceed one agent’s abilities, including mathematical and scientific question answering, games, robotics, and clinical decisions. Common approaches include role-specialized agents, chain-of-thought debate and critique, voting or mixture-of-agents aggregation, and learned routing that decides who should contribute and when. Other work trains collaboration with reinforcement learning or distills group reasoning into a single model, while benchmarks test coordination under partial information and strategic interaction. A central tension is that collaboration can correct individual errors, but communication costs, correlated mistakes, and pressure to conform can erase its gains; when it helps depends on the task, evidence quality, and compute budget.

Latest papers

233 papers29 papers in the last four weeks, up 142% on the four weeks before. 0.2% of all new papers.

Distilling Bayesian Belief States into Language Models for Auditable Negotiation
May 6, 2026Zongqi Cui, Baihan LinMulti-Agent Negotiation Opponent Modeling
Emory University · Icahn School of Medicine at Mount Sinai
A Study of Belief Revision Postulates in Multi-Agent Systems (Extended Version)
May 4, 2026Michael Thielscher, Tran Cao SonMulti-Agent Reasoning
University of New South Wales, Sydney, Australia · New Mexico State University, Las Cruces, New Mexico, USA
Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling
May 2, 2026Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle +2Self-Consistency Decoding Cost-Aware Inference
University of Göttingen, Germany
Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents
May 2, 2026Shijun Lei, Hongyu Wang, Yunji Liang +3Knowledge Conflicts in Language Models Social Bias in Language Models
Northwestern Polytechnical University · Central University of Finance and Economics
Agents and Tokens: Multi-Agent Autonomous Reasoning over a Hydrodynamic Token Store
May 1, 2026Jinpai Zhao, Albert Cerrone, Joannes Westerink +1Multi-Agent Orchestration AI Agents for Scientific Discovery
Oden Institute University of Texas at Austin Austin, Texas, USA · CEEES University of Notre Dame Notre Dame, Indiana, USA
AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems
May 1, 2026Ivan LetteriMulti-Agent Orchestration AI Agent Safety
Department of Information Engineering, Computer Science, and Mathematics, Center of Excellence for Research DEWS, University of L’Aquila, Via Vetoio, Coppito, 67100 L’Aquila, Italy
The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms
Apr 30, 2026Dahlia Shehata, Ming LiMulti-Agent LLM Systems Multi-Agent Coordination
University of Waterloo · Canada
Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation
Apr 29, 2026Ariel SelaMulti-Agent LLM Systems Multi-Agent Coordination
Tel Aviv University
I Would If I Could: Reasoning about Dynamics of Actions in Multi-Agent Systems
Apr 28, 2026Rustam Galimullin, Hermine Grosinger, Munyque MittelmannMulti-Agent Systems Multi-Agent Reasoning
University of Bergen, Bergen, Norway · Örebro University, Örebro, Sweden · CNRS, UMR 7030, F-93430, Villetaneuse, France +1
StratFormer: Adaptive Opponent Modeling and Exploitation in Imperfect-Information Games
Apr 28, 2026Andy Caen, Mark H. M. Winands, Dennis J. N. J. SoemersOpponent Modeling Game-Playing Agents
Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands
Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
Apr 27, 2026John Seon Keun Yi, Aaron Mueller, Dokyun LeeMulti-Agent Debate Language Model Distillation
Boston University
QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems
Apr 27, 2026Chenyang An, Qihao Ye, Minghao Pan +1AI Agents for Scientific Discovery Automated Theorem Proving
University of California, San Diego, La Jolla, USA · California Institute of Technology, Pasadena, USA · Amazon Web Services
Don't Make the LLM Read the Graph: Make the Graph Think
Apr 24, 2026Yuqi Sun, Tianqin Meng, George Liu +4Multi-Agent Coordination Game-Playing Agents
Mindoverflow · University of Waterloo · Carnegie Mellon University +4
Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
Apr 23, 2026Ye Yu, Heming Liu, Haibo Jin +3Multi-Agent System Optimization LLM Agent Training
University of Illinois Urbana-Champaign, IL, USA
HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration
Apr 23, 2026Yuehan Zhu, Jingqi Zhao, Jiawen Zhao +2Multi-Agent Collaboration Multimodal QA
School of Artificial Intelligence, Sun Yat-sen University, China
Information Aggregation with AI Agents
Apr 21, 2026Spyros GalanisAI Agent Evaluation Multi-Agent Reasoning
Department of Economics, University of Durham
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
Apr 21, 2026Bobo Li, Rui Wu, Zibo Ji +5AI Agent Benchmarks Multi-Agent Reasoning
National University of Singapore · Sichuan University · University of Minnesota Twin Cities +2
Revac: A Social Deduction Reasoning Agent
Apr 21, 2026Mihir Shriniwas Arya, Avinash Anish, Aditya RanjanGame-Playing Agents Social Deduction Games
Department of Computer Science and Engineering RV College of Engineering Bangalore · Department of Information Science and Engineering RV College of Engineering Bangalore · Department of Artificial Intelligence and Machine Learning RV College of Engineering Bangalore
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
Apr 20, 2026Xingchen Xiao, Heyan Huang, Runheng Liu +1Retrieval-Augmented Generation Multi-Agent LLM Systems
School of Computer Science and Technology, Beijing Institute of Technology · Department of Mathematical Sciences, Tsinghua University
The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration
Apr 18, 2026Jiayuan Liu, Shiyi Du, Weihua Du +2Multi-Agent LLM Systems Adversarial Robustness
Carnegie Mellon University · Foundations of Cooperative AI Lab (FOCAL) · Adelaide University
Federation over Text: Insight Sharing for Multi-Agent Reasoning
Apr 18, 2026Dixi Yao, Tahseen Rabbani, Manzil Zaheer +1Multi-Agent LLM Systems Multi-Agent Reasoning
University of Chicago · Google DeepMind
SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems
Apr 17, 2026Hikaru Shindo, Hanzhao Lin, Lukas Helff +2LLM Agent Evaluation AI Agent Benchmarks
Technical University of Darmstadt · German Research Center for Artificial Intelligence · CERTAIN +2
Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
Apr 17, 2026Haoyu Bian, Chaoning Zhang, Jiaquan Zhang +4Multi-Agent Collaboration Inference-Time Compute Allocation
University of Electronic Science and Technology of China, Chengdu 611731, China · Beihang University, Beijing 100191, China · Xi’an University of Architecture and Technology, Xi’an 710064, China
Preregistered Belief Revision Contracts
Apr 16, 2026Saad AlqithamiBelief Revision Dynamic Epistemic Logic
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
Apr 16, 2026Yi Zhao, Yajuan Peng, Cam-Tu Nguyen +4Efficient Language Model Reasoning LLM Inference Acceleration
AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Shanghai Key Laboratory for Intelligent Information Processing, Fudan University · State Key Laboratory for Novel Software Technology, Nanjing University +2
Foresight Optimization for Strategic Reasoning in Large Language Models
Apr 15, 2026Jiashuo Wang, Jiawen Duan, Jian Wang +6Multi-Agent Reasoning RL for Language Model Reasoning
Department of Computing, Hong Kong Polytechnic University · Department of Language Science and Technology, Hong Kong Polytechnic University · Apple +3
Towards Autonomous Mechanistic Reasoning in Virtual Cells
Apr 13, 2026Yunhui Jang, Lu Zhu, Jake Fawkes +3Scientific Reasoning in Language Models Multi-Agent Reasoning
Korea Advanced Institute of Science and Technology (KAIST) · Valence Labs · Recursion +1
MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding
Apr 10, 2026Henry Zheng, Chenyue Fang, Rui Huang +33D Spatial Reasoning 3D Scene Understanding
Tsinghua University · Pico, ByteDance
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
Apr 7, 2026Changgeon Ko, Jisu Shin, Hoyun Song +3Multi-Agent LLM Systems LLM Agent Reliability
Korea Advanced Institute of Science and Technology (KAIST)
EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering
Apr 6, 2026Jiatan Huang, Zheyuan Zhang, Kaiwen Shi +2LLM Agent Routing Multi-Agent Collaboration
University of Connecticut, USA · University of Notre Dame, USA

May 6, 2026J/K move · Enter open · S save

Distilling Bayesian Belief States into Language Models for Auditable Negotiation

Zongqi Cui, Baihan Lin

Emory University · Icahn School of Medicine at Mount Sinai

Multi-Agent Negotiation Opponent Modeling Automated Negotiation LLM Auditing Language Model Calibration Language Model Distillation+1

Open paper AskPDF arXiv

Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but their opponent beliefs are usually implicit and difficult to inspect. We propose BOND (Bayesian Opponent-belief Negotiation Distillation), a framework for auditable negotiation. BOND consists of an LLM-based Bayesian teacher that scores dialogue contexts against the six possible opponent priority orderings, updates a posterior over those orderings, and uses the posterior for menu-based decision making, as well as a smaller 8B student language model that emits both negotiation actions and normalized posterior beliefs as tagged text. In the CaSiNo negotiation dataset, BOND outperforms the state-of-the-art and achieves mean Brier score 0.085 over opponent-priority posteriors. The distilled student preserves much of this belief signal, achieving Brier 0.114, below the uniform six-ordering reference of 5/36, approximately 0.139. Compared with a 70B structured-CoT baseline, the significantly smaller 8B student model yields substantially better elicited posterior calibration. We further showcase auditability through posterior trajectories, belief-versus-policy error decomposition, and posterior-prefix interventions. These diagnostics reveal that distillation preserves a scoreable belief report more strongly than causal belief-conditioned control, making weak belief-action coupling visible, not hidden.