Multi-Agent LLM Systems

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

85 papers in the last four weeks, up 107% on the four weeks before. 0.8% of all new papers.

Jul 13Week of Sep 28

Latest papers 668

All topics

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems
May 26, 2026Yiqun Chen, Wei Yang, Erhan Zhang +14Multi-Agent LLM Systems Multi-Agent System Optimization
Renmin University of China · Xiaohongshu Inc.
Stateful Inference for Low-Latency Multi-Agent Tool Calling
May 25, 2026Victor NorgrenLLM Inference Efficiency Multi-Agent LLM Systems
LayerScale, Inc.
PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
May 25, 2026Daren Wang, Hong Xu, Jiawen XianMulti-Agent LLM Systems LLM Agent Orchestration
The Chinese University of Hong Kong · Evolution AI Lab
Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?
May 25, 2026Franka Bause, Jonas Niederle, Martin Pawelczyk +1Multi-Agent LLM Systems Opinion Dynamics
CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Faculty of Computer Science, University of Vienna, Vienna, Austria.
Multi-Agent Coordination Adaptation via Structure-Guided Orchestration
May 25, 2026Haoran Li, Shulun Chen, Shaoyuan Sun +1Multi-Agent LLM Systems Multi-Agent System Optimization
Nanjing University · University of Technology Sydney, Sydney, Australia · University of New South Wales, Sydney, Australia
AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
May 25, 2026Penghui Yang, Zhonghan Zhang, Yue Li +6Multi-Agent LLM Systems Scientific Workflow Automation
Nanyang Technological University, Singapore · Singapore Management University
ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy
May 25, 2026Xinkui Zhao, Sai Liu, Yifan Zhang +6Multi-Agent LLM Systems Multi-Agent System Optimization
Zhejiang University · Ningbo Global Innovation Center, Zhejiang University · Zhejiang Key Laboratory of Digital-Intelligence Service Technology +1
A Universal Cliff and a Design Fingerprint: Cross-Section Defect Detection Under LLM Orchestration
May 25, 2026Hiroki FukuiMulti-Agent LLM Systems LLM Evaluation
Research Institute of Criminal Psychiatry · Department of Neuropsychiatry, Graduate School of Medicine, Kyoto University
A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration
May 25, 2026Lipeng Dai, Luping Xiang, Kun YangMulti-Agent LLM Systems Multi-Agent Collaboration
State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, 210008, China · Institute of Intelligent Networks and Communications (NINE), Nanjing University (Suzhou Campus), Suzhou, 215163, China
Towards Reliable Fetal Ultrasound Interpretation with Multi-Agent Collaboration
May 25, 2026Xiaotian Hu, Mingxuan Liu, Junwei Huang +13Multi-Agent LLM Systems Medical VQA
Tsinghua University, Beijing, China · University of California San Diego, La Jolla, CA, USA · West China Second University Hospital, Sichuan University, Chengdu, China
LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design
May 24, 2026Leshu Li, An Lu, Haiyu Wang +5Multi-Agent LLM Systems Materials Science
New York University, USA · University of Illinois Chicago, USA
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs
May 24, 2026Yi Li, Songtao Wei, Dongming Jiang +3Multi-Agent LLM Systems Multi-Agent System Optimization
University of Texas at Dallas · Independent Researcher · University of California, Davis
MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
May 24, 2026Magnus Samuelsen, Wilmer Nyström, Somnath Mazumdar +2Financial Services Multi-Agent LLM Systems
Copenhagen Business School, Solbjerg Plads 3, Frederiksberg, 2000, Denmark · Jyske Bank, Copenhagen, Denmark
MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
May 23, 2026Roberto Cruz, David Rey-BlancoMulti-Agent LLM Systems Healthcare
TietAI
Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis
May 23, 2026Zhimin Lin, Kun Cheng, Zhiyao Shu +4Multi-Agent LLM Systems LLM-Assisted Annotation
Soochow University · George Mason University · Johns Hopkins University
Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
May 23, 2026Yunhua Pei, Zerui Ge, Jin Zheng +1Multi-Agent LLM Systems Multi-Agent Systems
University of Bristol, UK · Independent Researcher
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
May 22, 2026Yifan Zeng, Yiran Wu, Yaolun Zhang +4Multi-Agent LLM Systems LLM Agent Workflow Optimization
1Oregon State University · 2Pennsylvania State University · 3Adobe Inc. +1
LLM-driven design of physics-constrained constitutive models: two agents are better than one
May 22, 2026Marius Tacke, Matthias Busch, Kian Abdolazizi +4Neural Surrogate Modeling Multi-Agent LLM Systems
1Helmholtz-Zentrum Hereon, Geesthacht, Germany · 2Hamburg University of Technology, Hamburg, Germany · 3RWTH Aachen University, Aachen, Germany +2
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
May 22, 2026Zehao Wang, Shilong Jin, Zhao Cao +1Multi-Agent LLM Systems Multi-Agent Planning
College of Intelligence and Computing, Tianjin University, Tianjin, China · School of New Media and Communication, Tianjin University, Tianjin, China · Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
Symbolic Reasoning Frameworks Trigger Memory-Mediated Ecosystem Dynamics in Multi-Agent LLM Systems
May 22, 2026Augustin ChanMulti-Agent LLM Systems Game-Playing Agents
Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework
May 22, 2026Hyunjee Park, Hayoung ChungTopology Optimization Multi-Agent LLM Systems
Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulju-gun, Ulsan, 44919, Republic of Korea
SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate
May 21, 2026Weifan Jiang, Rana Shahout, Minghao Li +4Multi-Agent LLM Systems Multi-Agent Debate
Harvard University
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
May 21, 2026Zeyu He, Hannah Kim, Dan Zhang +1Multi-Agent LLM Systems Process Supervision
Penn State University · Work done during internship at Megagon Labs · Megagon Labs
A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism
May 21, 2026Chuanbo Hu, Minglei Yin, Bin Liu +4Multi-Agent LLM Systems Autism Spectrum Disorder
Department of Computer Science, University at Albany, Albany, 12222, NY, USA. · Department of Management Information System, West Virginia University, Morgantown, 26506, WV, USA. · Humanities and Social Sciences, California Institute of Technology, Pasadena, 91125, CA,2026 USA. +1
Self-Evolving Multi-Agent Systems via Decentralized Memory
May 21, 2026Guangya Hao, Yunbo Long, Zhuokai ZhaoMulti-Agent LLM Systems LLM Agent Memory
University of Cambridge · University of Chicago
Claw AI Lab: An Autonomous Multi-Agent Research Team
May 21, 2026Fan Wu, Cheng Chen, Zhenshan Tan +12Multi-Agent LLM Systems LLM Agent Orchestration
1NTU · 2A*STAR · 4NUIST +3
One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems
May 21, 2026Yufei Shi, Weilong Yan, Naixuan Huang +5Multi-Agent LLM Systems Video Generation
MedVisAI Lab, Lee Kong Chian School of Medicine, Nanyang Technological University · National University of Singapore · Beijing Institute of Technology +2
Blind Spots in the Guard: How Domain-Camouflaged Injection Attacks Evade Detection in Multi-Agent LLM Systems
May 21, 2026Aaditya PaiMulti-Agent LLM Systems AI Agent Security
Data Science Institute Columbia University
Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
May 20, 2026Akshay Manglik, Vijay S. Kalmath, Jason Qin +6Multi-Agent LLM Systems LLM Agent Evaluation
Scale AI
Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis
May 20, 2026Juergen DietrichMulti-Agent LLM Systems Language Model Fingerprinting
Democracy Intelligence gGmbH, Berlin, Germany

May 26, 2026, cs.AIJ/K move · Enter open · S save

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

Yiqun Chen, Wei Yang, Erhan Zhang, Shijie Wang+13

Renmin University of China · Xiaohongshu Inc.

Multi-Agent LLM Systems Multi-Agent System Optimization LLM Agent Workflow Optimization LLM Agent Training RL for LLM Agents Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules, while agents are rarely optimized through a unified reinforcement learning interface. Existing RL post-training frameworks mainly target single-policy optimization and lack abstractions for user-defined multi-agent workflows, structured interaction, role-specific credit assignment, and configurable parameter sharing. We present UnityMAS-O, a general RL optimization framework for LLM-based multi-agent systems. UnityMAS-O treats the complete workflow as the optimization unit, rather than a single response or policy trajectory. It represents workflows through four first-class objects: logical agent roles, graph trajectories, user-defined rewards, and agent--model mappings. This decouples logical agents from physical model parameters, supporting full sharing, full separation, and partial sharing, with rewards assigned at role, turn, and trajectory levels. UnityMAS-O extends verl with a Ray-based star-topology runtime. A central controller executes workflows, invokes tools, records structured trajectories, and assembles rewards; model-local worker groups handle rollout, buffering, advantage computation, and distributed PPO-style updates. Users can define agents, workflows, model mappings, and rewards without rewriting the optimization infrastructure. We instantiate UnityMAS-O on retrieval-augmented QA, iterative agentic search, and reflective code generation. Across Natural Questions, HotpotQA, and held-out code tasks, multi-agent RL improves manually specified workflows after optimization, with especially large gains for smaller models and strict code all-passed metrics. These results show that UnityMAS-O can serve as a reusable substrate for converting diverse LLM-based multi-agent workflows into trainable multi-agent RL systems.

Momentum

Related topics

Latest papers 668