Autonomous Multidisciplinary Decision Intelligence Platform Using Agentic AI, Knowledge Graphs, and Digital Twins

  • Authors

    • Seppo Linnainmaa Professor of Computer Science, University of Helsinki, Finland. Author
    • Arto Salomaa Professor of Computer Science, University of Turku, Finland. Author

    DOI:

    https://doi.org/10.67228/30715636/IJETMR-2025PI8U3R

    Published 05-03-2025

  • Agentic Artificial Intelligence, Autonomous Decision Intelligence, Knowledge Graphs, Digital Twins, Explainable Artificial Intelligence, Intelligent Agents, Semantic Reasoning, Reinforcement Learning, Cyber-Physical Systems, Enterprise Intelligence, Autonomous Systems, Multidisciplinary Decision Support

    Issue

    Vol. 8 No. 1 (2025)

    Section

    Articles

  • Abstract

    This paper presents the Autonomous Multidisciplinary Decision Intelligence Platform (AMDIP), which integrates Agentic AI, Knowledge Graphs, and Digital Twin technologies to enable autonomous, explainable, and adaptive decision-making across multiple domains. By combining semantic reasoning, predictive simulation, continuous learning, and intelligent agent collaboration, the framework improves decision accuracy, operational efficiency, scalability, and resilience in dynamic cyber-physical environments. The proposed architecture offers a scalable and extensible foundation for next-generation enterprise intelligence, supporting complex multidisciplinary decision-making through real-time knowledge integration, autonomous optimization, and transparent AI-driven reasoning.

  • References

    [1] Y. LeCun, Y. Bengio, and G. Hinton, "Deep Learning," Nature, vol. 521, no. 7553, pp. 436–444, 2021.

    [2] T. Brown et al., "Language Models are Few-Shot Learners," Advances in Neural Information Processing Systems, vol. 34, pp. 1877–1901, 2021.

    [3] J. Bommasani et al., "On the Opportunities and Risks of Foundation Models," Stanford University, 2022.

    [4] OpenAI, "GPT-4 Technical Report," 2023.

    [5] C. Sutton and A. Barto, Reinforcement Learning: An Introduction, 2nd ed., MIT Press, 2021.

    [6] R. S. Sutton, "The Bitter Lesson Revisited," IEEE Intelligent Systems, vol. 37, no. 5, pp. 8–15, 2022.

    [7] J. Pearl, The Book of Why: The New Science of Cause and Effect, Updated Edition, 2022.

    [8] L. Zhou, H. Wang, and Y. Li, "Autonomous Multi-Agent Decision Systems: A Survey," IEEE Access, vol. 10, pp. 60245–60271, 2022.

    [9] X. Wang, Z. Li, and M. Chen, "Collaborative Multi-Agent Reinforcement Learning for Intelligent Decision Making," IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 8, pp. 4788–4802, 2023.

    [10] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed., Pearson, 2022.

    [11] T. Schick et al., "Toolformer: Language Models Can Teach Themselves to Use Tools," 2023.

    [12] Q. Chen, H. Zhang, and Y. Liu, "Agent-Based Artificial Intelligence: Recent Advances and Future Directions," IEEE Access, vol. 11, pp. 80123–80145, 2023.

    [13] J. Chen et al., "AutoGen: Enabling Next-Generation Large Language Model Applications," Microsoft Research, 2023.

    [14] S. Hong et al., "MetaGPT: Meta Programming for Multi-Agent Collaborative Frameworks," 2023.

    [15] M. Shinn et al., "Reflexion: Language Agents with Verbal Reinforcement Learning," 2023.

    [16] Gajula, S. (2024). Cybersecurity risk prediction using graph neural networks. Journal of Information Systems Engineering and Management.

    [17] Gajula, S. (2024). Adaptive zero trust architecture for securing financial microservices. Computer Fraud & Security, 2024(12), 643–655. https://doi.org/10.52710/cfs.845

  • Downloads