A Multi-Agent Workflow Orchestration System for Complex Long-Cycle Tasks

Article Sidebar

PDF
Published: Aug 21, 2026
DOI: https://doi.org/10.7716/aem.v15i3.4269
Keywords:
Access control Dynamic workflow Long-cycle tasks Multi-Agent system

Main Article Content

Y. T. Qin
University of Electronic Science and Technology of China
Z. C. Lu
University of Electronic Science and Technology of China
L. H. Wu
University of Electronic Science and Technology of China
J. C. Zhao
University of Electronic Science and Technology of China
T. Y. Lyu
University of Electronic Science and Technology of China

Abstract

A dynamic workflow orchestration system with the control plane separated from the execution plane is proposed to address the problem that traditional hard-coded service orchestration cannot handle business process changes and service failures in long-cycle tasks. The system uses a Multi-Agent architecture, through the division of roles such as the orchestration engine Agent, task execution Agent, and user Agent, combined with directory service (DF) registration and QOS-driven Contract Network Protocol (CNP), to achieve dynamic service selection and delay binding for flexible activities. An access control model based on dynamic binding of roles and tasks (R-TBAC) is introduced to enable dynamic granting and revocation of permissions driven by task instances.

Downloads

Download data is not yet available.

Article Details

How to Cite
Qin, Y. T., Lu, Z. C., Wu, L. H., Zhao, J. C., & Lyu, T. Y. (2026). A Multi-Agent Workflow Orchestration System for Complex Long-Cycle Tasks. Advanced Electromagnetics, 15(3), 10648–10656. https://doi.org/10.7716/aem.v15i3.4269
Issue
Vol. 15 No. 3 (2026)
Section
Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

References

Q. Zhu, “The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale,” arXiv:2606.12835 [cs.MA], Jun. 2026.

J. Li et al., “Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application,” arXiv:2606.12191 [cs.CL], Jun. 2026.

H.-T. Liao, C.-Y. Kao, and K. Ang, “Trustworthy Smart Fabs via Professional Proxies: Scaling Safe and Sustainable by Design (SSbD) through Industrial Data Spaces,” arXiv:2606.09227 [cs.CR], Jun. 2026.

Y. Sun et al., “PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting,” arXiv:2606.08878 [cs.CL], Jun. 2026.

K. Wang et al., “Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems,” arXiv:2606.08661 [cs.CR], Jun. 2026.

D. Zhang and L. Liaotian, “Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestration,” arXiv:2606.06545 [cs.SE], Jun. 2026.

J. Xu, “OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection,” arXiv:2606.03161 [cs.MA], Jun. 2026.

P. Qin, Q. Cao, and P. Xie, “ATLAS: Agentic Test-time Learning-to-Allocate Scaling,” arXiv:2606.01667 [cs.LG], Jun. 2026.

R. Li et al., “Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory,” arXiv:2606.01385 [cs.SE], Jun. 2026.

J. Zhu et al., “Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems,” arXiv:2606.01351 [cs.AI], May 2026.

S. Sarangi et al., “EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations,” arXiv:2605.30258 [cs.MA], May 2026.

S. Gao, A. Fang, and M. Zitnik, “AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation,” arXiv:2605.28655 [cs.AI], May 2026.

C. Luo et al., “From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians’ Medical Expertise with Lightweight LLM,” arXiv:2603.23520 [cs.CL], Mar. 2026.

J. Cook et al., “Training a Large Language Model for Medical Coding Using Privacy-Preserving Synthetic Clinical Data,” arXiv:2603.23515 [cs.CL], Mar. 2026.

D. Joshi and I. Rekik, “HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature,” arXiv:2603.23136 [cs.CL], Mar. 2026.

Y. Wang et al., “RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset,” arXiv:2603.11811 [cs.RO], Mar. 2026.

Y. Yang et al., “Implement Kubernetes Pod-Level Remote Attestation for Confidential Workloads on dstack,” arXiv:2605.03323 [cs.CR], Jun. 2026.

S. Ling et al., “Free-Riding in the AI Economy: Demystifying Logic Flaws in x402-Enabled Payment Systems,” arXiv:2605.30998 [cs.CR], May 2026.

J. Chen et al., “NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding,” arXiv:2605.21100 [cs.DC], May 2026.

M. A. Bouchia et al., “DARTIC: Decentralized Anonymous Reputation at Scale for Trustworthy Crowdsourcing,” arXiv:2605.18146 [cs.CR], May 2026.

S. Liu, S. Shin, and D. Deka, “Watts vs. Bytes: Turning Data Centers into Grid Assets via Storage Compute Co-Optimization,” arXiv:2605.16190 [eess.SY], May 2026.

S. Wu et al., “Look One Step Ahead: Forward-Looking Incentive Design with Strategic Privacy for Proactive Service Provisioning over Air-Ground Integrated Edge Networks,” arXiv:2604.13635 [cs.NI], Apr. 2026.

S. Liu, P. J. Elahi, and U. Varetto, “HPC-vQPU: A Service-Export Architecture for Virtual QPUs on Batch-Scheduled HPC Systems,” arXiv:2605.28845 [cs.DC], May 2026.

M. Waseem et al., “Engineering a Governance-Aware AI Sandbox: Design, Implementation, and Lessons Learned,” arXiv:2603.03394 [cs.SE], Mar. 2026.

P. Yan et al., “FWeb3: A Practical Incentive-Aware Federated Learning Framework,” arXiv:2603.00666 [cs.DC], Feb. 2026.

M. Besta et al., “GraphSeek: Next-Generation Graph Analytics with LLMs,” arXiv:2602.11052 [cs.DB], Mar. 2026.

M. Goenka, T. Pathak, and S. Asthana, “TessPay: Verify-then-Pay Infrastructure for Trusted Agentic Commerce,” arXiv:2602.00213 [cs.CR], Feb. 2026.

H. KimLee et al., “QuantumSavory: Write Symbolically, Run on Any Backend – A Unified Simulation Toolkit for Quantum Computing and Networking,” arXiv:2512.16752 [quant-ph], Dec. 2025.

H. Derouiche, Z. Brahmi, and H. Mazeni, “Agentic AI Frameworks: Architectures, Protocols, and Design Challenges,” arXiv:2508.10146 [cs.AI], Aug. 2025.

S. Saxena, H. Farag, H. Turesson, and H. M. Kim, “Blockchain Based Transactive Energy Systems for Voltage Regulation,” arXiv:1907.08725 [cs.CR], Jul. 2019.

S. Kaur, H. Kaur, and S. Kaur Sehra, “Modification of Contract Net Protocol(CNP): A Rule-Updation Approach,” arXiv:1312.4259 [cs.MA], Dec. 2013.

B. Megdouda et al., “LLM-Based Digital Twin Intelligence for Application-Aware Network Selection in 6G Heterogeneous Wireless Networks,” arXiv:2606.12293 [eess.SP], Jun. 2026.

Y. Chen et al., “Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference,” arXiv:2606.05933 [cs.DO], Jun. 2026.

M. H. D. Saria Allahham and H. S. Hassanein, “How Reliable is Your Service at the Extreme Edge? Analytical Modeling of Computational Reliability,” arXiv:2602.16362 [cs.DO], Feb. 2026.

G. A. Ubiali et al., “Joint Subarray Selection, User Scheduling, and Pilot Assignment for XL-MIMO,” arXiv:2601.13470 [eess.SP], Jan. 2026.