Multi-Agent Orchestration

Follow this topic Ask about this topic

Multi-agent orchestration studies how to divide work among AI agents, assign roles, manage communication, and combine results for tasks that are too complex or long-running for one agent. Common approaches include hierarchical planner–worker systems, dependency graphs and parallel execution, adaptive routing among specialized agents, and decentralized coordination through markets or peer networks. Researchers also develop verification, shared memory, recovery, and policy controls, evaluating systems on coding, research, enterprise workflows, scientific computing, and robotics. A central tension is that more coordination can improve coverage and reliability but also adds latency, cost, and new failure or safety risks, so effective systems must adapt their structure to the task and operating constraints.

Latest papers

207 papers30 papers in the last four weeks, up 76% on the four weeks before. 0.2% of all new papers.

MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems
Oct 28, 2026Hehai Lin, Qi Yang, Chengwei QinMulti-Agent Orchestration Multi-Agent System Optimization
The Hong Kong University of Science and Technology (Guangzhou) · Ant Group
GEAR: Feature-Based Configuration and Code Generation for Agentic Systems
Oct 26, 2026Brell Sanwouo, Nada Zine, Paul Temple +2Agentic Code Generation Multi-Agent Systems
Univ. Lille, CNRS, Inria, UMR 9189 CRIStAL, Lille, France · Univ. Rennes, CNRS, Inria, IRISA, Rennes, France · Institut Universitaire de France (IUF), Paris, France
Agentic AI Orchestration Framework for Spatial Intelligence: Supply Chain Deployment
Oct 25, 2026Constantinos Papantoniou, Brian HiltonAI Agent Architecture Multi-Agent Orchestration
Anassa.ai USA · Research Scientist USA
DynaFlow: Learning Free-Form Multi-Agent Orchestration
Oct 25, 2026Ruhao Liu, Qi Li, Shizun Wang +1Multi-Agent Orchestration LLM Agent Orchestration
National University of Singapore
PULSES: multi-agent AI for autonomous excited-state model building and dynamics
Oct 23, 2026Fangning Ren, Lechen Dong, Xu Chen +3AI Agents for Scientific Discovery Autonomous Research Agents
Department of Chemistry, Emory University, Atlanta, GA, 30322, USA
Mining the Design Space of Multi-Agent Workflows
Oct 22, 2026Xavier Cadet, Junyan Cheng, Peter Chin +1Multi-Agent Orchestration LLM Agent Workflow Optimization
Dartmouth College · Allen Institute for AI
RoleFlow: Self-Evolving Multi-Role Agentic Collaboration via Structural Adaptation
Oct 21, 2026Yi Ge, Pan Wang, Xuehao Cui +4Multi-Agent LLM Systems LLM Agent Workflow Optimization
University of Maryland, College Park · University of Pittsburgh · The University of Texas at Dallas
Agentic Orchestration of EDC Data Space Retrieval and Natural Language Driven Data Processing
Oct 19, 2026Marla Grunewald, Fin Gentzen, Iulisloi Zacarias +1Multi-Agent Orchestration Tool Access Control for LLM Agents
Institute of Computer and Network Engineering, Technische Universität Braunschweig, Germany
FRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds
Oct 15, 2026Ohad Dan, Abhinav TaliyanMulti-Agent Orchestration AI Agent Architecture
Learning Self-Orchestration in Decentralized Agent Swarms
Oct 15, 2026Guowei Xu, Zhenting Qi, Amani Kiruga +2Multi-Agent Orchestration Multi-Agent Coordination
Harvard University
HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
Oct 15, 2026Yanchen Deng, Jianguo Huang, Yao Long Teng +6Multi-Agent Orchestration LLM Agent Orchestration
Nanyang Technological University, Singapore · Apodex.
A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems
Oct 15, 2026Thi-Nhung Nguyen, Viet-Thanh Pham, Linhao Luo +2Multi-Agent Coordination Multi-Agent Systems
Department of Data Science & AI, Monash University
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
Oct 13, 2026Yiqing Peng, Hehai Lin, Zixuan Wang +7Multi-Agent Coordination Multi-Agent LLM Systems
The Hong Kong University of Science and Technology (Guangzhou) · Wake Forest University · University of Science and Technology of China +1
MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification
Oct 13, 2026Hehai Lin, Zixuan Wang, Ming Yan +6LLM Agent Workflow Optimization Multi-Agent Orchestration
The Hong Kong University of Science and Technology (Guangzhou) · Sun Yat-sen University · National University of Singapore +2
AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment
Oct 12, 2026Yinzhu Quan, Zefang Liu, Frederick Benaben +1Supply Chain Management LLM Agents
Physical Internet Center, H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, 30332, GA, USA · School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, 30332, GA, USA · Centre Genie Industriel, IMT Mines Albi, Albi, France
OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains
Oct 12, 2026Xunkai Li, Miao Zhang, Zekai Chen +6Multi-Agent LLM Systems Multi-Agent Systems
Competence-Aware Orchestration for LLM-Based Multi-Agent Systems
Oct 9, 2026Songmiao Wang, Yuchen Wang, Chenglin Yu +2LLM Agent Orchestration Multi-Agent LLM Systems
The Hong Kong Polytechnic University
DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning
Oct 6, 2026Jie Ren, Jiakang Yuan, Chenyu Huang +3Multi-Agent Collaboration Multi-Agent Reasoning
College of Future Information Technology, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China
OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation
Oct 6, 2026Qi Cheng, Shengyu Chen, Wei Cheng +4Multi-Agent Systems Multi-Agent Orchestration
Rutgers University New Brunswick, NJ · University of Pittsburgh Pittsburgh, PA · NEC Labs America Princeton, NJ +1
Decoupled Multi-Agent Orchestration
Oct 6, 2026Xinle Wu, Yao LuMulti-Agent Orchestration LLM Agent Orchestration
National University of Singapore
CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration
Oct 5, 2026Yixin Zhang, Wenjie FengTraining Data Curation Multi-Agent Orchestration
University of Science and Technology of China
Orchestrating Level- $K$ Policies Against Unknown Opponents in Partially-Observable Dynamic Games
Oct 4, 2026Addison Kalanther, Sanika Bharvirkar, Daniel Bostwick +2Multi-Agent Orchestration Multi-Agent Reinforcement Learning
EECS, University of California, Berkeley, CA, USA · ECE, Johns Hopkins University, Baltimore, MD, USA
AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems
Oct 3, 2026Muhammad Bilal Awan, Zubair Hussain, Abdul ShahidAgentic Workflows Automated Program Repair
Ministry of Defense, Doha, Qatar · IQRA University, Islamabad, Pakistan · South East Technological University, Waterford, Ireland
Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization
Oct 1, 2026Xuehang Guo, Haoyu Wang, Shengyu Chen +4Multi-Agent Coordination Multi-Agent Orchestration
William & Mary · NEC Corporation of America
Can AI Scientists Coordinate at Runtime?
Oct 1, 2026Zijian Liu, Yangzhixin Luo, Junyu Lu +6Multi-Agent Coordination Multi-Agent Orchestration
University of Oxford · King Abdullah University of Science and Technology · University of Sydney +1
Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems
Oct 1, 2026Asad Ur Rehman, Syed Mohammad Kashif, Ruiyin Li +3Multi-Agent LLM Systems Multi-Agent Orchestration
School of Computer Science, Wuhan University, China · School of Computer Science & Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning, Central China Normal University, China · M3S Empirical Software Engineering Research Unit, University of Oulu, Finland
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
Sep 29, 2026Mingda Zhang, Hanwen Zhang, Qiang Huang +5Multi-Agent Orchestration Agent Skill Learning
The Chinese University of Hong Kong, Shenzhen, China · Dalian University of Technology, China · Fudan University, China +3
Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation
Sep 29, 2026Genliang Zhu, Chu WangRuntime Enforcement for AI Agents Multi-Agent Orchestration
Accentrust, Vancouver, Canada · Georgia Institute of Technology, Atlanta, Georgia, USA · University of Illinois Urbana-Champaign, Urbana, Illinois, USA
PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems
Sep 29, 2026Matthew D. Laws, Cristina Nita-RotaruMulti-Agent LLM Systems Multi-Agent Orchestration
Khoury College of Computer Sciences Northeastern University
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
Sep 29, 2026Prithwish Jana, Mononito Goswami, Hao Liu +9Multi-Agent Orchestration Evolutionary Optimization
Georgia Institute of Technology · AWS AI Labs · Carnegie Mellon University +1

Oct 28, 2026J/K move · Enter open · S save

MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems

Hehai Lin, Qi Yang, Chengwei Qin

The Hong Kong University of Science and Technology (Guangzhou) · Ant Group

Multi-Agent Orchestration Multi-Agent System Optimization Self-Evolving Agents

Open paper AskPDF arXiv

Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes and learns from its terminal outcome. This paradigm discards execution trajectories that expose system-level failures and contain fine-grained information beyond the terminal outcome, leaving no direct basis for revising the source MAS, evaluating the updated MAS, or learning from the resulting contrast. To this end, we introduce MAS-Loop, an execution-grounded framework that closes this feedback loop by coupling an Orchestrator with a trajectory-conditioned Refiner. For each task, the Orchestrator constructs and executes a source MAS to obtain an outcome score and an intermediate trajectory. Conditioned on the trajectory, the Refiner localizes an actionable failure, formulates a trajectory-grounded diagnosis, and proposes a bounded patch to the agents, information flow, or execution configuration. The executable updated MAS is re-executed on the same task to measure its realized outcome under stochastic execution. This pair-MAS comparison provides complementary learning signals: the Orchestrator learns to generate strong systems with fewer recoverable failures, whereas the Refiner learns to expose and repair observed weaknesses, thereby driving policy-level co-evolution across training iterations. Experiments show that MAS-Loop achieves the strongest overall performance among the evaluated baselines, with consistent gains from refinement across all evaluated benchmarks. The co-evolution process also yields MAS-JudgeCorpus, a dataset of execution-grounded source-updated pairs with orchestration- and trajectory-level supervision, which can provide the community with support for MAS reward modeling and trajectory-aware investigation.