Multi-Agent LLM Systems

LLM: Large Language Model

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

1,050 papers142 papers in the last four weeks, up 35% on the four weeks before. 0.8% of all new papers.

VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
May 7, 2026Keisuke Kamahori, Shihang Li, Simon Peter +1Multi-Agent LLM Systems LLM Serving
University of Washington
Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
May 7, 2026Huchen Yang, Xinghao Dong, Dan Negrut +1Multi-Agent LLM Systems Multi-Agent System Optimization
University of Wisconsin–Madison
Design Conductor 2.0: An agent builds a TurboQuant inference accelerator in 80 hours
May 6, 2026The Verkor Team, Ravi Krishna, Suresh Krishna +1AI Accelerator Inference Multi-Agent LLM Systems
The Verkor Team
SODE: Analyzing Social Dynamics in LLM Agents
May 6, 2026Inseo Jung, Yoonseok Oh, Kyungryul Back +2Multi-Agent LLM Systems LLM Agent Evaluation
Department of Computer Science, Korea University · Kakao Mobility
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
May 6, 2026Jiangwen Dong, Bo Li, Wanyu LinMulti-Agent LLM Systems Scientific Hypothesis Generation
1The Hong Kong Polytechnic University · 2The Hong Kong University of Science and Technology
SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition
May 6, 2026Naiyu Zheng, Tianlong Yu, Haochen Yin +3Multi-Agent LLM Systems Human Activity Recognition
City University of Hong Kong Hong Kong · Hubei University China · The Chinese University of Hong Kong Hong Kong +1
Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining
May 5, 2026Achuth Chandrasekhar, Omid Barati Farimani, Radheesh Sharma Meda +1Multi-Agent LLM Systems Document Information Extraction
Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Biomedical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA +2
Governed Collaborative Memory as Artificial Selection in LLM-Based Multi-Agent Systems
May 5, 2026Diego F. Cuadros, Abdoul-Aziz Maiga, Helen Meskhidze +1Multi-Agent LLM Systems LLM Agent Memory
Digital Epidemiology Laboratory, Digital Futures, University of Cincinnati, Cincinnati, OH, USA · Department of Biological Sciences, University of Cincinnati, Cincinnati, OH, USA · Center for Humanities and Technology (CHaT), University of Cincinnati, Cincinnati, OH, USA +2
Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing
May 5, 2026Danny Hoang, Ryan Matthiessen, Christopher Miller +5Manufacturing Multi-Agent LLM Systems
School of Mechanical, Aerospace, and Manufacturing Engineering, University of Connecticut, Storrs, CT, USA · Connecticut Center for Advanced Technology, East Hartford, CT, USA · Quinnipiac University, Hamden, CT, USA +1
QKVShare: Quantized KV-Cache Handoff for Multi-Agent On-Device LLMs
May 5, 2026Pratik Honavar, Tejpratap GVSLMixed-Precision Quantization Multi-Agent LLM Systems
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
May 5, 2026Shinas Shaji, Teena Chakkalayil Hassan, Sebastian Houben +1Multi-Agent LLM Systems Theory of Mind
Institute of AI and Autonomous Systems (A2S), Hochschule Bonn-Rhein-Sieg, Grantham-Allee 20, Sankt Augustin, 53757, Germany. · 3Fraunhofer Institute for Intelligent Analysis and Information SystemsMay (IAIS), Schloss Birlinghoven, Sankt Augustin, 53757, Germany. · 2Division for Systems and Control, Chalmers University of Technology, Chalmersplatsen 1, Gothenburg, 41296, Sweden.
LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing
May 5, 2026Ahmadreza Eslaminia, Chuhan Cai, Cameron Smith +5Multi-Agent LLM Systems Industrial Anomaly Detection
Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA · Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA · Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI 48109, USA +1
Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems
May 5, 2026Maksym Nechepurenko, Pavel ShuvalovMulti-Agent LLM Systems Multi-Agent Coordination
Devnull FZCO · Dubai, UAE
From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry
May 4, 2026Aritra Roy, Kevin Shen, Andrew MacBride +350Multi-Agent LLM Systems AI Agents for Scientific Discovery
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
May 4, 2026Ruofeng Yang, Yongcan Li, Shuai LiAI Agent Reliability Multi-Agent LLM Systems
Shanghai Jiao Tong University · Shanghai Innovation Institute
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
May 4, 2026Chenchen ZhangMulti-Agent LLM Systems LLM Agent Orchestration
Independent Researcher
ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling
May 4, 2026Guangrui XieMulti-Agent LLM Systems Large Language Model-Guided Optimization
From Experimental Limits to Physical Insight: A Retrieval-Augmented Multi-Agent Framework for Interpreting Searches Beyond the Standard Model
May 4, 2026Altan Cakir, Ayca YerlikayaMultimodal RAG Multi-Agent LLM Systems
Istanbul Technical University, Department of Data Science and Analytics, Istanbul, Turkey · Istanbul Technical University, Department of Physics Engineering, Istanbul, Turkey
When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems
May 4, 2026Jose Manuel de la Chica, Juan Manuel Vera, Jairo RodríguezMulti-Agent LLM Systems AI Agent Evaluation
Santander AI Lab
EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions
May 4, 2026Xiyuan Zhou, Ruixi Zou, Xinlei Wang +4Multi-Agent LLM Systems Software Engineering Agents
Nanyang Technological University · The Chinese University of Hong Kong, Shenzhen · INSAIT, Sofia University “St. Kliment Ohridski” +2
CyberAId: AI-Driven Cybersecurity for Financial Service Providers
May 3, 2026George Fatouros, Georgios Makridis, John Soldatos +18Multi-Agent LLM Systems Autonomous Cyber Defense
Innov-Acts, Cyprus · University of Piraeus, Greece · Unparallel Innovation, Portugal +7
Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems
May 3, 2026Yue Ma, Ziyuan Yang, Yi ZhangMulti-Agent LLM Systems Jailbreak Defense
Sichuan University · Nanyang Technological University
CP-SynC: Multi-Agent Zero-Shot Constraint Modeling in MiniZinc with Synthesized Checkers
May 3, 2026Yuliang Song, Eldan CohenMulti-Agent LLM Systems LLM-Based Program Synthesis
Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, Canada
Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse
May 2, 2026Ahmed F. IbrahimMulti-Agent LLM Systems Requirements Engineering
Western University London, Canada
DiagramNet: An End-to-End Recognition Framework and Dataset for Non-Standard System-Level Diagrams
May 2, 2026Jincheng Lou, Ruohan Xu, Jiapeng Li +6Multi-Agent LLM Systems Electronic Design Automation
School of IC, Peking University, Beijing, China · College of Artificial Intelligence, Xi’an Jiaotong University, Xi’an, China · Department of Precision Instruments, Tsinghua University, Beijing, China +4
FeedbackLLM: Metadata driven Multi-Agentic Language Agnostic Test Case Generator with Evolving prompt and Coverage Feedback
May 2, 2026Kushal Jasti, Tejamani Prashanth Sahu, Rishitha Pentyala +2Multi-Agent LLM Systems Automated Software Testing
Department of Computer Science and Engineering, SRM University AP, India
RunAgent: Interpreting Natural-Language Plans with Constraint-Guided Execution
May 1, 2026Arunabh Srivastava, Mohammad A., Khojastepour +2Multi-Agent LLM Systems Tool-Using Language Agents
Amir · University of Maryland, College Park, MD · 2NEC Laboratories America, Inc.
Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
May 1, 2026Aninda RayLLM Inference Efficiency Multi-Agent LLM Systems
The $\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations
Apr 30, 2026Aurélien Bück-Kaeffer, Sneheel Sarangi, Maximilian Puelma Touzel +3Multi-Agent LLM Systems Human Behavior Simulation
McGill University · Mila - Quebec Artificial Intelligence Institute · Ubisoft La Forge +2
RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems
Apr 30, 2026Jiacheng Liu, Zichen Tang, Zhongjun Yang +8Multi-Agent LLM Systems LLM Planning
Beijing University of Posts and Telecommunications · The Hong Kong University of Science and Technology (Guangzhou) · IDEA Research +1

May 7, 2026J/K move · Enter open · S save

VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?

Keisuke Kamahori, Shihang Li, Simon Peter, Baris Kasikci

University of Washington

Multi-Agent LLM Systems LLM Serving AI Coding Agents

Open paper AskPDF arXiv

For years, we have built LLM serving systems like any other critical infrastructure, with a single general-purpose stack hand-tuned over many engineer-years to support every model and workload. In this paper, we take the opposite bet and let coding agents automatically synthesize bespoke serving systems for different usage scenarios. We propose VibeServe, the first agentic loop that generates entire LLM serving stacks end-to-end. VibeServe uses an outer loop to plan and track the search over system designs, and an inner loop to implement candidates, check correctness, and measure performance on the target benchmark. In standard serving settings, VibeServe matches vLLM and SGLang on Llama-3.1-8B, and delivers 2.3x the goodput of a tuned SGLang for a 397B MoE model on four AMD MI300As. In five non-standard scenarios, VibeServe outperforms existing systems by exploiting opportunities that generic systems miss, spanning non-standard model architectures, workload knowledge, and hardware-specific optimizations. Together, these results argue that infrastructure software should favor generation-time specialization over runtime generality. Code is available at https://github.com/uw-syfi/vibesys.