Multi-Agent LLMs

LLM: Large Language Model

Ask about this topic

Overview

Multi-agent large language models study how multiple language-model-powered agents can divide work, communicate, use tools, and combine their decisions. Common approaches assign specialized roles, use debate or verification, route tasks adaptively, and maintain shared memory; newer systems also learn communication protocols or exchange compressed internal representations. Applications range from reasoning and software development to clinical support, scientific discovery, social simulation, and strategic games. A central tension is that collaboration can improve performance but also adds cost and can spread errors, bias, or unsafe behavior, while benchmarks still struggle to measure reliable long-horizon coordination.

Latest papers

CardsList

324 papers33 papers in the last four weeks, up 14% on the four weeks before. 0.2% of all new papers.

  1. Communicating about Space: Language-Mediated Spatial Integration Across Partial Views

    Mar 28, 2026Ankur Sikarwar, Debangan Mishra, Sudarshan Nikhil +2Spatial Reasoning in Language ModelsSpatial Reasoning

    Mila – Quebec AI Institute · Université de Montréal · IIIT Hyderabad +1

  2. MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination

    Mar 25, 2026Zhuo Li, Yupeng Zhang, Pengyu Cheng +8LLM Hallucination MitigationLLM Hallucination Detection

    Qwen Large Model Application Team, Alibaba · The Chinese University of Hong Kong, Shenzhen

  3. Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios

    Mar 25, 2026Li Ma, Hao Peng, Yiming Wang +6Game-Playing AgentsSelf-Evolving Agents

    School of Cyber Science and Technology, Beihang University, Beijing 100191, China · Naval Aviation University, Yantai 264001, China · Military Science Academy, Beijing 100091, China +3

  4. TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents

    Mar 23, 2026Minghan Li, Rachel Gonsalves, Weiyue Li +2Algorithmic TradingLLM Agent Reliability

    Harvard AI and Robotics Lab, Harvard University . · Harvard Business School, Harvard University . · Daegu Gyeongbuk Institute of Science and Technology . +1

  5. Revisiting Gene Ontology Knowledge Discovery with Hierarchical Feature Selection and Virtual Study Group of AI Agents

    Mar 20, 2026Cen Wan, Alex A. FreitasAutonomous Scientific DiscoveryMulti-Agent LLMs

    School of Computing and Mathematical Sciences, Birkbeck, University of London, London, United Kingdom. · School of Computing, University of Kent, Canterbury, United Kingdom.

  6. GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems

    Mar 20, 2026Hongjiang Chen, Xin Zheng, Yixin Liu +7Multi-Agent Communication TopologyMulti-Agent Communication

    School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China · School of Computing Technologies, RMIT University, Melbourne, Australia · School of Information and Communication Technology, Griffith University, Goldcoast, Australia

  7. Book your room in the Turing Hotel! A symmetric and distributed Turing Test with multiple AIs and humans

    Mar 19, 2026Christian Di Maio, Tommaso Guidi, Luigi Quarantiello +4LLM EvaluationHuman-AI Interaction

    DIISM, University of Siena, Italy · Department of Computer Science, University of Pisa, Italy · LUISS University, Rome, Italy

  8. TopoChunker: Topology-Aware Agentic Document Chunking Framework

    Mar 19, 2026Xiaoyu LiuDocument ChunkingStructured RAG

    Independent Researcher, Beijing, China

  9. VeriAgent: A Tool-Integrated Multi-Agent System with Evolving Memory for PPA-Aware RTL Code Generation

    Mar 18, 2026Yaoxiang Wang, Qi Shi, ShangZhan Li +6RTL Code GenerationElectronic Design Automation

    Xiamen University · Tsinghua University · Harbin Institute of Technology

  10. Adaptive Theory of Mind for LLM-based Multi-Agent Coordination

    Mar 17, 2026Chunjiang Mu, Ya Zeng, Qiaosheng Zhang +6Multi-Agent CoordinationMulti-Agent Systems

    School of Cybersecurity, Northwestern Polytechnical University · Shanghai Artificial Intelligence Laboratory · Huawei Noah’s Ark Lab +2

  11. SAGE: Multi-Agent Self-Evolution for LLM Reasoning

    Mar 16, 2026Yulin Peng, Xinxin Zhu, Chenxing Wei +4LLM ReasoningSelf-Training for Language Models

    College of Computer Science and Software Engineering, Shenzhen University, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), China · School of Information Technology, Carleton University, Canada

  12. Scaling Laws for Educational AI Agents

    Mar 12, 2026Mengsong Wu, Hao Hao, Shuzhen Bi +5AI in EducationGenerative AI in Education

    East China Normal University · Shanghai Innovation Institute

  13. Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning

    Mar 10, 2026Lina Berrayana, Ahmed Heakl, Abdullah Sohail +3Multi-Agent ReasoningMulti-Agent LLMs

    EPFL · MBZUAI · ETH Zürich +1

  14. Collective AI can amplify tiny perturbations into divergent decisions

    Mar 10, 2026Hajime Shimao, Warut Khern-am-nuai, Sung Joo KimLLM Decision-MakingMulti-Agent LLMs

    The Pennsylvania State University, Malvern, PA, USA · McGill University, Montreal, QC, Canada · American University, Washington, DC, USA

  15. Quantifying Divergence in Inter-LLM Communication Through API Retrieval and Ranking

    Mar 9, 2026Eyhab Al-MasriLLM EvaluationLLM Agent Reliability

    School of Engineering and Technology, University of Washington (Tacoma)

  16. Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA

    Mar 9, 2026Ummar Abbas, Mourad Ouzzani, Mohamed Y. Eltabakh +7Question AnsweringLLM Grounding

    Qatar Computing Research Institute, HBKU, Qatar

  17. MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus

    Mar 5, 2026Zheng Li, Jiayi Xu, Zhikai Hu +4Medical DiagnosisClinical Decision Support

    School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China · School of Artificial Intelligence, Jilin University, Changchun, 130015, China · Department of Neurology, China-Japan Union Hospital of Jilin University, Changchun, 130033, China +2

  18. A Multi-Agent Framework for Interpreting Multivariate Physiological Time Series

    Mar 4, 2026Davide Gabrielli, Paola Velardi, Stefano Faralli +1Explainable Artificial IntelligenceMulti-Agent LLMs

    Sapienza University of Rome Rome, Italy · ISTC-CNR & Sapienza University of Rome Rome, Italy · Technical University of Munich Munich, Germany

  19. AI4S-SDS: A Neuro-Symbolic Solvent Design System via Sparse MCTS and Differentiable Physics Alignment

    Mar 4, 2026Jiangyu ChenLarge Language Model-Guided Scientific DiscoveryNeuro-Symbolic AI

    State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University · Suzhou Laboratory

  20. OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents

    Mar 3, 2026Yichao Feng, Haoran Luo, Zhenghong Lin +4Multi-Agent LLMsMulti-Agent Orchestration

    Magellan Technology Research Institute (MTRI) · Nanyang Technological University, Singapore

  21. Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization

    Mar 3, 2026Yueyang Cang, Xiaoteng Zhang, Erlu Zhao +7Communication Topology OptimizationMulti-Agent Communication Topology

    Tsinghua University · Donghua University

  22. Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis

    Mar 2, 2026Zice Wang, Zhenyu ZhangFraming Effects in Language ModelsMulti-Agent LLMs

    Northeastern University, Shenyang 110819, Liaoning, China. · Beijing Institute of Technology, Beijing, 100081, China.

  23. RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse

    Feb 28, 2026Yingsheng Geng, Yuchong Gao, Weihong Wu +2LLM Inference AccelerationKV-Cache Reuse

    Beijing University of Posts and Telecommunications, Beijing, China · Tsinghua University, Beijing, China · University of Electronic Science and Technology of China, Chengdu, China +1

  24. MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games

    Feb 27, 2026Jacob Eisenstein, Fantine Huot, Adam Fisch +2LLM EvaluationMulti-Turn Dialogue Evaluation

    Google DeepMind

  25. From Tokens To Agents: A Researcher's Guide To Understanding Large Language Models

    Feb 27, 2026Daniele BaroloLanguage ModelingLLM Alignment

  26. Can Agents Distinguish Visually Hard-to-Separate Diseases in a Zero-Shot Setting? A Pilot Study

    Feb 26, 2026Zihao Zhao, Frederik Hauke, Juliana De Castilhos +2Medical Image ClassificationMultimodal Agents

    Department of Diagnostic and Interventional Radiology, University Hospital Aachen, 52074 Aachen, Germany

  27. Reasoning-Driven Design of Single Atom Catalysts via a Multi-Agent Large Language Model Framework

    Feb 25, 2026Dong Hyeon Mok, Seoin Back, Victor Fung +1Materials ScienceLarge Language Model-Guided Scientific Discovery

    Department of Chemical and Biomolecular Engineering, Institute of Emergent Materials, Sogang University, Seoul 04107, Republic of Korea · KU-KIST Graduate School of Converging Science and Technology, Korea University, Seoul 02841, Republic of Korea · Department of Integrative Energy Engineering, Korea University, Seoul 02841, Republic of Korea +4

  28. Evaluating Theory of Mind and Internal Beliefs in LLM-Based Multi-Agent Systems

    Feb 24, 2026Adam Kostka, Jarosław A. ChudziakMulti-Agent LLMsMulti-Agent Collaboration

    Warsaw University of Technology, Poland

  29. Agentic Framework for Political Biography Extraction

    Feb 23, 2026Yifei Zhu, Songpo Yang, Jiangnan Zhu +1Document Information ExtractionLLM Information Extraction

    Ph.D candidate, Department of Politics and Public Administration, The University of Hong Kong. · Boya Postdoctoral Fellow, School of International Studies, Peking University. · Associate Professor, Department of Politics and Public Administration, The University of Hong Kong. +1

  30. Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems

    Feb 23, 2026Moritz Weckbecker, Jonas Müller, Ben Hagag +1Multi-Agent System SecurityMulti-Agent Systems

    Fraunhofer HHI, Berlin, Germany · Eleuther AI · TU Berlin, Berlin, Germany +2