Design of a Multi-Agent-Based Agentic AI Architecture for Decision-Making Optimization in Intelligent Information Systems

Honghui Mingyu

Authors

Honghui Mingyu Honghui Mingyu Department of Systems Engineering, City University of Hong Kong, Hong Kong

Keywords:

Agentic Artificial Intelligence, Multi-Agent Systems, Intelligent Information Systems, Decision-Making Optimization, AI-Based Decision Support

Abstract

Modern decision-making in intelligent information systems has become increasingly complex due to the growing volume, heterogeneity, and uncertainty of information that organizations must process. Conventional intelligent information systems and traditional decision-support approaches often have limited capabilities in autonomous reasoning, dynamic planning, multi-objective optimization, and adaptation to changing decision environments. The emergence of Agentic AI provides an opportunity to address these limitations through autonomous perception, reasoning, planning, tool use, and action execution. Furthermore, multi-agent collaboration enables complex decision problems to be distributed among specialized agents with complementary capabilities. This study aims to design and evaluate a Multi-Agent-Based Agentic AI architecture for decision-making optimization in intelligent information systems. The study adopts a Design Science Research approach combined with experimental evaluation. The proposed architecture consists of specialized Perception/Data, Analysis, Planning, Optimization, Critic/Validation, and Decision Agents coordinated through an inter-agent communication mechanism and supported by a multi-objective optimization model. The system is evaluated experimentally using decision accuracy, optimization performance, response time, robustness, and comparison with baseline approaches, including rule-based DSS, traditional optimization, single-agent AI, and conventional multi-agent AI. The experimental evaluation is intended to determine whether the proposed architecture provides measurable improvements in decision quality and robustness. Overall, the study demonstrates the potential of Multi-Agent Agentic AI as an approach for complex decision-making by combining specialized reasoning, autonomous planning, collaborative validation, and optimization.

References

Anumba, C. J., Ugwu, O. O., Newnham, L., & Thorpe, A. (2002). Collaborative design of structures using intelligent agents. Automation in Construction, 11(1), 89–103.

Bordini, R. H., El Fallah Seghrouchni, A., Hindriks, K., Logan, B., & Ricci, A. (2020). Agent programming in the cognitive era. Autonomous Agents and Multi-Agent Systems, 34(2), 37.

Chowdhury, G. G. (2010). Introduction to modern information retrieval. Facet publishing.

Fu, R., Zhang, Y., Zhang, S., Wu, X., Gu, W., Wang, F., Che, Z., Liu, X., Sun, Y., & Zhang, Y. (2018). Collaborative Knowledge Distillation and Reinforcement Learning for Automated Ticket Triage in Large-Scale Production Systems. ACM Transactions on Software Engineering and Methodology.

Guo, M., Yang, Y., Xu, R., Liu, Z., & Lin, D. (2020). When nas meets robustness: In search of robust architectures against adversarial attacks. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 628–637.

Haq, A. U., Li, J. P., Memon, M. H., Malik, A., Ahmad, T., Ali, A., Nazir, S., Ahad, I., & Shahid, M. (2019). Feature selection based on L1-norm support vector machine and effective recognition system for Parkinson’s disease using voice recordings. IEEE Access, 7, 37718–37734.

Heylighen, F. (2015). Stigmergy as a Universal Coordination Mechanism: components, varieties and applications. Human Stigmergy: Theoretical Developments and New Applications; Springer: New York, NY, USA.

Kazman, R., Asundi, J., & Klein, M. (2002). Making architecture design decisions: An economic approach. Carnegie Mellon University, Software Engineering Institute Pittsburgh.

Khemakhem, F., Ellouzi, H., Ltifi, H., & Ayed, M. Ben. (2020). Agent-based intelligent decision support systems: a systematic review. IEEE Transactions on Cognitive and Developmental Systems, 14(1), 20–34.

Liu, H. (2014). On advancing business intelligence in the electricity retail market. Turku Centre for Computer Science (TUCS).

Luck, M., McBurney, P., & Preist, C. (2004). A manifesto for agent technology: Towards next generation computing. Autonomous Agents and Multi-Agent Systems, 9(3), 203–252.

Mahdavifar, S., & Ghorbani, A. A. (2020). DeNNeS: deep embedded neural network expert system for detecting cyber attacks. Neural Computing and Applications, 32(18), 14753–14780.

Mattiev, J., & Kavšek, B. (2020). A compact and understandable associative classifier based on overall coverage. Procedia Computer Science, 170, 1161–1167.

Mishra, S., Tripathy, H. K., Mallick, P. K., Bhoi, A. K., & Barsocchi, P. (2020). EAGA-MLP—an enhanced and adaptive hybrid classification model for diabetes diagnosis. Sensors, 20(14), 4036.

Mortazavi, A., Khamseh, A. A., & Azimi, P. (2015). Designing of an intelligent self-adaptive model for supply chain ordering management system. Engineering Applications of Artificial Intelligence, 37, 207–220.

Myers, K., Berry, P., Blythe, J., Conley, K., Gervasio, M., McGuinness, D., Morley, D., Pfeffer, A., Pollack, M., & Tambe, M. (2007). An intelligent personal assistant for task and time management. Ai Magazine, 28(2), 47–61.

Ridderinkhof, K. R., Van Den Wildenberg, W. P. M., Segalowitz, S. J., & Carter, C. S. (2004). Neurocognitive mechanisms of cognitive control: the role of prefrontal cortex in action selection, response inhibition, performance monitoring, and reward-based learning. Brain and Cognition, 56(2), 129–140.

Rossi, S., Di Napoli, C., Barile, F., & Liguori, L. (2016). Conflict Resolution Profiles and Agent Negotiation for Group Recommendations. WOA, 29–34.

Sleight, J. L. (2015). Agent-Driven Representations, Algorithms, and Metrics for Automated Organizational Design.

Srivastava, B., & Koehler, J. (2003). Web service composition-current solutions and open problems. ICAPS 2003 Workshop on Planning for Web Services, 35, 28–35.

Torreno, A., Onaindia, E., Komenda, A., & Štolba, M. (2017). Cooperative multi-agent planning: A survey. ACM Computing Surveys (CSUR), 50(6), 1–32.

Vercellis, C. (2011). Business intelligence: data mining and optimization for decision making. John Wiley & Sons.

Villa, D. K. D., Brandao, A. S., & Sarcinelli-Filho, M. (2020). A survey on load transportation using multirotor UAVs. Journal of Intelligent & Robotic Systems, 98(2), 267–296.

Yang, Q. (2012). Intelligent planning: a decomposition and abstraction based approach. Springer Science & Business Media.

Zhang, Z., & Zhang, C. (2004). Agent-based hybrid intelligent systems: An agent-based framework for complex problem solving. Springer.