IJCCCS
Call For Paper
Submission Guidelines Plagiarism Policy Processing Charges
Reviewer Guidelines Join as Peer Reviewer
Editorial Board
Latest Issue Past Issue
Home / Archives / Volume 1 Issue 1
RESEARCH ARTICLE

Agentic Cloud Intelligence: Architectures for Autonomous Reasoning, Planning, and Self-Optimization in Distributed Cloud Ecosystems

Todorov Iliev, Dinev Pavlov
IJCCCS Journal Cover
International Journal of Cloud Computing and Cyber Security
© 2026 by IJCCCS
VOLUME Volume 1
ISSUE Issue 1
PUBLICATION January 2026
PAGES 61-78
DOI 10.xxxx/ijcccs.v1i1p05
FULL TEXT Download PDF
CITATION

How to Cite This Article

Todorov Iliev, Dinev Pavlov, 2026. "Agentic Cloud Intelligence: Architectures for Autonomous Reasoning, Planning, and Self-Optimization in Distributed Cloud Ecosystems" , IJCCCS , Volume 1, Issue 1, pp. 61-78.
ARTICLE SUMMARY

Abstract

“”

Agentic Cloud Intelligence is the next-generation paradigm in which autonomous AI agents employ distributed cloud computing infrastructures to build intelligent adaptive self-managing cloud ecosystems. Today, traditional cloud management approaches continue to struggle under the onslaught of dynamic workloads, resource complexity and real-time operational demands due to increasing dependence on cloud-native applications and big data analytics, IoT devices and edge computing services in modern organizations. Traditional cloud systems are highly dependent on established automation principles and human input, constraining their ability to react in real time to the variables of an evolving atmosphere. These limitations of contemporary cloud computing are recognized by Agentic Cloud Intelligence, which lets agents autonomously reason, plan, learn and optimize the operation with little to no human input. Agentic Cloud Intelligence architecture combines state-of-the-art technologies like machine learning, deep learning, reinforcement learning, large language models, knowledge graphs and multi-agent systems. These technologies provide automated ways for intelligent agents to sense the environmental context, reason through contextual information, make decisions, and autonomously perform actions. Cloud agents have the ability to perform intelligent functions through cognitive capabilities such as reasoning, planning, memory management and adaptive learning to continuously monitor infrastructure performance, make predictions of resource requirements, detect anomalies and optimize service delivery. Memory-augmented architectures additionally enable retention of knowledge and contextual understanding, enabling the agent to learn from decisions progressively.

INDEX TERMS

Keywords

“”

Cloud Computing / Cloud-Native Architecture, Multi-Agent Systems / Autonomous Agents, Distributed Cloud Computing, Intelligent Planning / Self-Optimization, Reinforcement Learning

  1. [1] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, NJ, USA: Pearson, 2021.
  2. [2] Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
  3. [3] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
  4. [4] M. Wooldridge, An Introduction to MultiAgent Systems, 2nd ed. Chichester, U.K.: Wiley, 2009.
  5. [5] N. R. Jennings and M. Wooldridge, “Applications of intelligent agents,” in Agent Technology: Foundations, Applications, and Markets. Berlin, Germany: Springer, 1998, pp. 3–28.
  6. [6] J. O. Kephart and D. M. Chess, “The vision of autonomic computing,” Computer, vol. 36, no. 1, pp. 41–50, Jan. 2003.
  7. [7] IBM Corporation, An Architectural Blueprint for Autonomic Computing, 4th ed. Armonk, NY, USA: IBM, 2006.
  8. [8] T. Erl, R. Puttini, and Z. Mahmood, Cloud Computing: Concepts, Technology & Architecture. Upper Saddle River, NJ, USA: Prentice Hall, 2013.
  9. [9] R. Buyya, J. Broberg, and A. Goscinski, Cloud Computing: Principles and Paradigms. Hoboken, NJ, USA: Wiley, 2011.
  10. [10] L. Kleinrock, “Communication nets: Stochastic message flow and delay,” New York, NY, USA: McGraw-Hill, 1964.
  11. [11] B. Burns, B. Grant, D. Oppenheimer, E. Brewer, and J. Wilkes, “Borg, Omega, and Kubernetes,” Communications of the ACM, vol. 59, no. 5, pp. 50–57, 2016.
  12. [12] B. Burns, J. Beda, and K. Hightower, Kubernetes: Up and Running, 3rd ed. Sebastopol, CA, USA: O’Reilly Media, 2022.
  13. [13] M. Fowler, Patterns of Enterprise Application Architecture. Boston, MA, USA: Addison-Wesley, 2002.
  14. [14] Gamma, R. Helm, R. Johnson, and J. Vlissides, Design Patterns: Elements of Reusable Object-Oriented Software. Reading, MA, USA: Addison-Wesley, 1994.
  15. [15] T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein, Introduction to Algorithms, 4th ed. Cambridge, MA, USA: MIT Press, 2022.
  16. [16] P. Bertsekas and J. N. Tsitsiklis, Neuro-Dynamic Programming. Belmont, MA, USA: Athena Scientific, 1996.
  17. [17] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
  18. [18] Newell and H. A. Simon, Human Problem Solving. Englewood Cliffs, NJ, USA: Prentice Hall, 1972.
  19. [19] S. J. Russell and E. H. Wefald, Do the Right Thing: Studies in Limited Rationality. Cambridge, MA, USA: MIT Press, 1991.
  20. [20] Shannon, “A mathematical theory of communication,” Bell System Technical Journal, vol. 27, no. 3, pp. 379–423, 1948.
  21. [21] M. Minsky, The Society of Mind. New York, NY, USA: Simon & Schuster, 1986.
  22. [22] Silver et al., “Mastering the game of Go with deep neural networks and tree search,” Nature, vol. 529, no. 7587, pp. 484–489, 2016.
  23. [23] Silver et al., “Mastering chess and shogi by self-play with a general reinforcement learning algorithm,” arXiv preprint arXiv:1712.01815, 2017.
  24. [24] T. Dean and M. Wellman, Planning and Control. San Francisco, CA, USA: Morgan Kaufmann, 1991.
  25. [25] M. Wooldridge, Reasoning About Rational Agents. Cambridge, MA, USA: MIT Press, 2000.
  26. [26] Garlan, S. W. Cheng, A. C. Huang, B. Schmerl, and P. Steenkiste, “Rainbow: Architecture-based self-adaptation with reusable infrastructure,” Computer, vol. 37, no. 10, pp. 46–54, 2004.
  27. [27] P. Horn, “Autonomic computing: IBM’s perspective on the state of information technology,” IBM Research, Yorktown Heights, NY, USA, 2001.
  28. [28] T. White, Hadoop: The Definitive Guide, 4th ed. Sebastopol, CA, USA: O’Reilly Media, 2015.
  29. [29] J. Dean and S. Ghemawat, “MapReduce: Simplified data processing on large clusters,” Communications of the ACM, vol. 51, no. 1, pp. 107–113, 2008.
  30. [30] Verma, L. Pedrosa, M. Korupolu, D. Oppenheimer, E. Tune, and J. Wilkes, “Large-scale cluster management at Google with Borg,” Proceedings of the European Conference on Computer Systems (EuroSys), pp. 1–17, 2015.