Elaris Computing Nexus
Hierarchical Multi Agent Intelligence Framework for Autonomous Task Composition in Distributed Computational Ecosystems
Elaris Computing Nexus
Received On : 06 March 2026
Revised On : 12 April 2026
Accepted On : 16 April 2026
Published On : 25 April 2026
Volume 02, 2026
Pages : 067-079
Abstract
Computational ecosystems that operate in a distributed manner are increasingly complex. The same can be said about adaptive and intelligent methods which can self-organize and integrate various classes of tasks in a dynamic and resource limited environment. Centralized techniques often have limitations in scalability, face high communication overhead, and tend to be inflexible in dealing with large-scale distributed systems. In this paper, a Hierarchical Multi-Agent Intelligence Framework (HMAIF) will be introduced to autonomously allocate, schedule, and manage resources, and execute tasks using multi-agent intelligence and hierarchical decision-making on system tasks that are fault-aware. The proposed framework is a multi-layered system that has strategic, domain-based, and execution-oriented agents for aware and context-specific decision making and decentralized task management. The dynamic nature of the framework with load balancing and inter-agent communication, makes it capable of adapting to varying computational, resource, and environmental demands. Furthermore, a hierarchical coordination model is introduced, which increased composition efficiency and system adaptability in large-scale distributed computing systems, while decreasing composition latency. The proposed framework provides the ability to partition and prioritize tasks, construct schedules, and implement intelligent recovery from failures of a partial nature to improve operational reliability. The framework is designed to counter the problems posed by multi-layered, distributed intelligent computing systems ranging from the cloud to the edge, cyber-physical systems, and intelligent distributed systems. Experimental results indicate that the framework provides an advanced and scalable distributed intelligent system solution, which meets the critical performance metrics of next generation autonomous distributed computing systems.
Keywords
Multi-Agent, Autonomous Task, Task Completion Time, Resource Utilization, Scalability, Throughput.
- M. Ghavamzadeh, S. Mahadevan, and R. Makar, "Hierarchical multi-agent reinforcement learning," Autonomous Agents and Multi-Agent Systems, vol. 13, no. 2, pp. 197–229, Apr. 2006, doi: 10.1007/s10458-006-7035-4.
- T. Ma, K. Peng, H. Rong, Y. Qian, and N. Al-Nabhan, "Hierarchical coordination multi-agent reinforcement learning with spatio-temporal abstraction," IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 8, no. 1, pp. 533–547, Feb. 2024, doi: 10.1109/TETCI.2023.3309738.
- J. Jin and X. Ma, "Hierarchical multi-agent control of traffic lights based on collective learning," Engineering Applications of Artificial Intelligence, vol. 68, pp. 236–248, Feb. 2018, doi: 10.1016/j.engappai.2017.10.013.
- T. Watanabe, "Hierarchical reinforcement learning using a modular fuzzy model for multi-agent problem," in New Advances in Machine Learning, Feb. 2010, doi: 10.5772/9388.
- Y. Bai, Y. Lv, and J. Zhang, "Smart mobile robot fleet management based on hierarchical multi-agent deep Q network towards intelligent manufacturing," Engineering Applications of Artificial Intelligence, vol. 124, Art. no. 106534, Sep. 2023, doi: 10.1016/j.engappai.2023.106534.
- W. Zhang, T. Zhao, Z. Zhao, Y. Wang, and F. Liu, "An intelligent strategy decision method for collaborative jamming based on hierarchical multi-agent reinforcement learning," IEEE Transactions on Cognitive Communications and Networking, vol. 10, no. 4, pp. 1467–1480, Aug. 2024, doi: 10.1109/TCCN.2024.3373640.
- O. E. Dragomir and F. Dragomir, "A decentralized hierarchical multi-agent framework for smart grid sustainable energy management," Sustainability, vol. 17, no. 12, Art. no. 5423, Jun. 2025, doi: 10.3390/su17125423.
- Y. Tang, J. Sun, H. Wang, J. Deng, L. Tong, and W. Xu, "A method of network attack-defense game and collaborative defense decision-making based on hierarchical multi-agent reinforcement learning," Computers & Security, vol. 142, Art. no. 103871, Jul. 2024, doi: 10.1016/j.cose.2024.103871.
- Y. Jiao et al., "A hierarchical hybrid learning framework for multi-agent trajectory prediction," IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 8, pp. 10344–10354, Aug. 2024, doi: 10.1109/TITS.2024.3357479.
- J. Wu, C.-J. Wang, J. Wang, and S.-F. Chen, "Dynamic hierarchical distributed intrusion detection system based on multi-agent system," in Proc. IEEE/WIC/ACM Int. Conf. Web Intelligence and Intelligent Agent Technology Workshops, Dec. 2006, pp. 89–93, doi: 10.1109/WI-IATW.2006.61.
- A. M. Seid, H. N. Abishu, R. S. Rathore, A. Erbad, R. H. Jhaveri, and J. Lu, "Blockchain-empowered multi-domain resource trading in TN-NTN 6G networks: A hierarchical multi-agent DRL approach," IEEE Transactions on Consumer Electronics, vol. 71, no. 2, pp. 3874–3889, May 2025, doi: 10.1109/TCE.2024.3512581.
- Y. Li, "Hierarchical architecture for multi-agent reinforcement learning in intelligent game," in Proc. Int. Joint Conf. Neural Networks (IJCNN), Jul. 2022, pp. 1–8, doi: 10.1109/IJCNN55064.2022.9892666.
- D.-H. Tran et al., "Network digital twin for 6G and beyond: An end-to-end view across multi-domain network ecosystems," IEEE Open Journal of the Communications Society, vol. 6, pp. 6866–6911, 2025, doi: 10.1109/OJCOMS.2025.3599866.
- X. Li, Y. Li, J. Zhang, X. Xu, and D. Liu, "A hierarchical multi-agent allocation-action learning framework for multi-subtask games," Complex & Intelligent Systems, vol. 10, no. 2, pp. 1985–1995, Oct. 2023, doi: 10.1007/s40747-023-01255-5.
- Q. Fu, T. Qiu, J. Yi, Z. Pu, and X. Ai, "Self-clustering hierarchical multi-agent reinforcement learning with extensible cooperation graph," IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 9, no. 2, pp. 1688–1698, Apr. 2025, doi: 10.1109/TETCI.2024.3449873.
- L. Bedogni, M. Mamei, M. Picone, M. Pietri, and F. Zambonelli, "Fluid computing and digital twins for intelligent interoperability in the IoT ecosystem," Future Generation Computer Systems, vol. 171, Art. no. 107855, Oct. 2025, doi: 10.1016/j.future.2025.107855.
- K.-C. Chen, S. Y.-C. Chen, C.-Y. Liu, and K. K. Leung, "Toward large-scale distributed quantum long short-term memory with modular quantum computers," in Proc. Int. Wireless Communications and Mobile Computing (IWCMC), May 2025, pp. 337–342, doi: 10.1109/IWCMC65282.2025.11059527.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript.
Acknowledgements
We would like to thank Reviewers for taking the time and effort necessary to review the manuscript. We sincerely appreciate all valuable comments and suggestions, which helped us to improve the quality of the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit: https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this Article
Vasily S. Petrenko, “Hierarchical Multi Agent Intelligence Framework for Autonomous Task Composition in Distributed Computational Ecosystems”, Elaris Computing Nexus, pp. 067-079, 2026, doi: 10.65148/ECN/2026006.
Copyright
© 2026 Vasily S. Petrenko. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.