Multi-Agent LLM Systems

LLM: Large Language Model

Overview

Multi-agent large language model systems study how multiple language-model agents can divide work, share information, and combine decisions on tasks such as reasoning, coding, research, and planning. Common designs use specialized roles, debate or review loops, retrieval-augmented generation, shared memory, and orchestrators that route tasks or choose communication links; some systems also learn prompts, workflows, or policies through reinforcement learning. Researchers evaluate these approaches on benchmarks for math, question answering, software, and tool use, as well as in longer-running simulations and domain applications. A central open tension is that collaboration can improve accuracy and verification, but may also add latency and token costs or spread errors, bias, and unsafe instructions, so gains depend on the task, architecture, and quality of coordination.

Latest papers

CardsList

1,119 papers91 papers in the last four weeks, down 35% on the four weeks before. 0.7% of all new papers.

  1. LM-based Personalized Travel Planner

    Nov 19, 2026Amandi Nimasha, Oshadha Wijerathne, Dushan Fernando +2Travel PlanningLLM Agent Planning

  2. Safe to Omit, Worth Omitting? Keeping the Answer and Cutting Latency When an LLM Agent Skips Another's Message

    Nov 17, 2026Xinyang Li, Chih-Hsuan Yang, Xiaolong Ma +4Multi-Agent LLM SystemsLLM Agent Efficiency

  3. TRACE-MAS: Diagnosing and Repairing Collaboration Failures in Multi-Agent Systems

    Nov 17, 2026Zekai Chen, Yihan Sun, Xunkai Li +6Multi-Agent LLM SystemsMulti-Agent Systems

  4. Inventa: Decentralized Self-Improving Agents for Autonomous Scientific Discovery

    Nov 16, 2026Prithwish Jana, Nikos Kanakaris, Purak Jain +2Autonomous Scientific DiscoveryResearch Idea Generation

  5. Corrupting Ties: Investigating Robustness to Bias Injection Across Multi-Agent Network Topologies

    Nov 16, 2026Cléa Chataigner, Mina Arzaghi, Florian Carichon +2Multi-Agent LLM SystemsMulti-Agent Systems

  6. GRACE: Parallel Best-of-N Multi-Agent Analysis of Closed-Form Questions over Dataframes with Guardrail Selection and Adaptive Retry

    Nov 16, 2026Fabio Picariello, Salvatore Cipolla, Susanna Bonura +1Table QAData Analysis Agents

  7. Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation

    Nov 16, 2026Yuanyan Song, Kezhi Wang, Xinmian Xu +1Multi-Agent LLM SystemsMulti-Agent Resource Allocation

  8. MASTA: A Feedback-Scheduled Multi-Agent System for End-to-End Tamarin Modeling and Analysis

    Nov 16, 2026Yongkang Xiao, Qiyi Deng, Jing Chen +3Formal VerificationMulti-Agent LLM Systems

  9. TrainExplorer: Autonomous LLM Post-Training via Plan-and-Decouple Exploration

    Nov 16, 2026Xuannan Liu, Tian Lan, Zekun Li +9LLM Post-TrainingLanguage Model Post-Training

  10. Macro Control and Capability Evaluation of Black-Box World Models: A Two-Regime Framework for LLM-Agent Markets

    Nov 14, 2026Zhiyang Niu, Chuanjie Li, Huayuan Shen +2LLM Agent EvaluationMulti-Agent LLM Systems

  11. When Should a Virtual Patient Ask? RISP-Guided Proactive Information Seeking in Multi-Agent Patient Simulation

    Nov 13, 2026Jingyao Cai, Shuaijun Liu, Abdul Rehman +5Educational Dialogue SystemsLarge Language Model-Based Role-Play Simulation

  12. Who Should Be on the Panel? Task-Conditioned Persona Selection for LLM Trading Agents

    Nov 13, 2026Boming Yang, Yuquan Wang, Jiaxian Guo +2Multi-Agent LLM SystemsAlgorithmic Trading

  13. More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs

    Nov 13, 2026Seyed Mahmoud Sajjadi MohammadabadiMulti-Agent LLM SystemsLLM Agent Evaluation

  14. Only as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent

    Nov 12, 2026Keegan Wang, Anantika MannbyLLM Agent SafetyLLM Agent Security

  15. Scalable Conversational Assessment: Chat-Based Exams with a Two-Agent LLM Pipeline

    Nov 12, 2026Geoffrey Challen, Craig ZillesEducationAutomated Evaluation

  16. MULTILOOP: Evolving Multi-Agent Harnesses for Complex Information-Seeking Tasks

    Nov 11, 2026Daniela Gottesman, Gal Yona, Ori Ram +4Agent Harness OptimizationMulti-Agent LLM Systems

  17. Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them

    Nov 9, 2026Shaohuang Wang, Jinghao Wen, Xulei Zhang +1Agent Failure AnalysisLLM Agent Reliability

  18. Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency Trading

    Nov 9, 2026Guangyan Gan, Jiahao Li, Jiashun Wang +1Cryptocurrency TradingAlgorithmic Trading

  19. Steering Emergent Behavior in Multi-Agent LLM Systems via Information Networks

    Nov 9, 2026Sepehr Ilami, Babak HeydariMulti-Agent LLM SystemsEmergent Behavior in Multi-Agent Systems

  20. Inside the Trading Loop: Markets, Models, and Moves with LLM Agents

    Nov 8, 2026Renee Jia, Di Mu, Yao Yu +1Portfolio ManagementAlgorithmic Trading