Overview

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

CardsList

242 papers12 papers in the last four weeks, down 57% on the four weeks before. 0.1% of all new papers.

  1. DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning

    Oct 6, 2026Jie Ren, Jiakang Yuan, Chenyu Huang +3Multi-Agent CollaborationMulti-Agent Reasoning

  2. Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help

    Oct 5, 2026Akshit Anchan, Nayonika SenMulti-Agent LLM SystemsMulti-Agent Reasoning

  3. Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia

    Oct 4, 2026Haonan Huang, Joey XiaoImperfect-Information GamesSocial Deduction Games

  4. When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning

    Oct 3, 2026Zihao Zhao, Tunyu Zhang, Haizhou Shi +3Multi-Agent DebateMulti-Agent Reasoning

  5. Revision-Aware Independent Agent Graphs for Dynamic Reasoning

    Oct 1, 2026Yan Luo, Selim-Antoine Lali, Jeremy Moebel +3Temporal ReasoningAI Agent Benchmarks

  6. From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

    Sep 29, 2026Jiayuan Chen, Botao Yu, Tianyu Liu +3Agentic ReasoningMulti-Agent Reasoning

  7. Solver Agent: an Agentic AI Framework for Theoretical Physics Computations Applied to F-theory Uplifts of O3-planes and S-folds

    Sep 28, 2026Eliott Morgensztern, Cesar Fierro Cota, Alessandro MininnoAI Agents for Scientific DiscoveryLLM Agent Verification

  8. Self-Adapting Group of Experts for Multi-Agent Reasoning

    Sep 28, 2026Mohammad Atif Quamar, Nurbek Tastan, Karthik Nandakumar +1Multi-Agent LLM SystemsMulti-Agent Reasoning

  9. TMCS: Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving

    Sep 28, 2026Shengqin Wang, Jie Jin, Yu Cheng +4Molecular OptimizationTool-Augmented Language Model Agents

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

    Sep 27, 2026Ruosong Ye, Caiqi Zhang, Jiahao Li +9Test-Time ScalingMulti-Agent Debate

  11. Self-Organizing Agent Teams Learn to Reason Together

    Sep 19, 2026Aneesh Pappu, Mirac Suzgun, Yongchan Kwon +5Self-Organizing Multi-Agent SystemsMulti-Agent Collaboration

  12. ToMAS: A Pilot Failure-Grounded Theory-of-Mind Benchmark from Multi-Agent LLM Failures

    Sep 15, 2026Muhammad Ashar Ishfaq, Glaucia MeloTheory of MindLLM Agent Evaluation

  13. Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science

    Sep 14, 2026Honghao Lin, David P. Woodruff, Yuan Deng +3Inference-Time SearchAutomated Theorem Proving

  14. DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact Checking

    Sep 12, 2026Yifei Li, Xiaohan Zheng, Wentao Qian +1Automated Fact-CheckingLLM Reasoning with Graphs

  15. Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference

    Sep 9, 2026Yaohan Guan, Yen-Ju Lu, Yuzhe Wang +5Spoken Language UnderstandingMulti-Agent Debate

  16. SRPO: Setwise Relative Policy Optimization for Multi-Agent Systems

    Sep 8, 2026Shengtian Yang, Ziyu Xiong, Yu Li +3Multi-Agent CoordinationPolicy Optimization

  17. From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration

    Sep 6, 2026Ala N. Tak, Teruhisa Misu, Kumar Akash +3Multi-Agent CollaborationMulti-Agent Reasoning

  18. Evidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical Referral

    Aug 31, 2026Qi Peng, Yi Cai, Jialin Cui +7Clinical Decision-MakingGraph Reasoning

  19. MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agents

    Aug 30, 2026Hei Ting Chan, Chenwei Wu, Xueshen Liu +4Agent MemoryAgent Memory Management

  20. One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles

    Aug 27, 2026Zhichen Zeng, Huiyuan Chen, Jingru Cheng +7Language Model SteeringMulti-Agent Reasoning

  21. Candidate supply and answer selection shape the value of LLM judging in multi-agent systems

    Aug 26, 2026Jia-Hao Ji, Sijie Li, Jiabei Cheng +3LLM-as-a-JudgeMulti-Agent Reasoning

  22. STRIVE: Multi-Agent Structured Temporal Reasoning with Integrated Verification for Longitudinal Radiology Report Generation

    Aug 25, 2026Junyeong Maeng, Eunsong Kang, Heung-Il SukRadiology Report GenerationTemporal Reasoning in Language Models

  23. From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM Reasoning

    Aug 23, 2026Vedant Khatri, Anthony Cusimano, Zachari Swiecki +3Multi-Agent ReasoningMulti-Agent Debate

  24. CARD: Diagnosing Belief to Action Routing Failures in Vision Language Models

    Aug 21, 2026Souptik Kumar Majumdar, Fabian Kögel, Andreas BullingVLM ReasoningReasoning for VLA Models

  25. Consilience: Conformally Calibrated Communication Control for Hidden-Profile Multi-Agent Reasoning

    Aug 20, 2026Abhijith Babu, Ramneet Kaur, Vishal Pramanik +7Multi-Agent CommunicationMulti-Agent LLM Systems