Citation :

Hitesh Chugani, "Agentic AI Systems: Architecture, Data Infrastructure, and Context Management," International Journal of Computer Trends and Technology (IJCTT), vol. 74, no. 2, pp. 16-29, 2026. Crossref, https://doi.org/10.14445/22312803/IJCTT-V74I2P104

Abstract

Artificial Intelligence has moved from reactive systems to systems that can reason, plan, and act over time. This shift has led to the development of Agentic Artificial Intelligence (Agentic AI). Unlike traditional AI systems that follow fixed input output rules, agentic AI systems maintain internal state, reason over context, plan multi-step actions, and interact with external environments with limited human input. This review places agentic AI within the historical development of agent-based artificial intelligence. It describes the main components of agentic systems, including perception, memory, goal management, execution, reflection, and orchestration. It also explains the data infrastructure required to support these systems. Traditional enterprise data platforms and stateless API-based integrations are not designed to support long-term reasoning, continuous context use, or dynamic tool interaction, which limits their suitability for agentic AI. A central focus of the paper is the Model Context Protocol (MCP), which provides a stateful interoperability layer that connects agents with external tools and data sources. MCP is compared with BDI architectures, classical multi-agent systems, and REST-based integration to explain its role and limitations. Security, implementation, and governance issues are also discussed. The review identifies research gaps in coordination, benchmarking, data integration, and secure deployment. Overall, the paper shows that agentic AI builds on earlier agent-based concepts using neural methods and requires layered architectures that combine reasoning models with interoperability standards.

Keywords

Agentic AI, Model Context Protocol (MCP), Autonomous AI Agents, Interoperability, Autonomous Agents.

References

[1] Dheer Toprani, and Vijay K. Madisetti, “LLM Agentic Workflow for Automated Vulnerability Detection and Remediation in Infrastructure-as-Code,” IEEE Access, vol. 13, pp. 69175–69181, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Ilias Chatzistefanidis, Andrea Leone, and Navid Nikaein, “Maestro: LLM-Driven Collaborative Automation of Intent-Based 6G Networks,” IEEE Networking Letters, vol. 6, no. 4, pp. 227–231, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Nalan Karunanayake, “Next-generation Agentic AI for Transforming Healthcare,” Informatics and Health, vol. 2, no. 2, pp. 73–83, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Joon Yul Choi, and Tae Keun Yoo, “Transforming Clinical Medicine with Multimodal Artificial Intelligence, Agentic Systems, and the Model-context Protocol : A Perspective on Future Directions,” Discover Health Systems, vol. 5, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Mohamad Abou Ali, Fadi Dornaika, and Jinan Charafeddine, “Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions,” Artificial Intelligence Review, vol. 59, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[6] IBM, What is agentic AI?. [Online]. Available: https://www.ibm.com/think/topics/agentic-ai

[7] Vallikranth Ayyagari, “Model Context Protocol for Agentic AI : Enabling Contextual Interoperability Across Systems,” International Journal of Computational and Experimental Science and Engineering, vol. 11, no. 3, 2025.
[CrossRef] [Publisher Link]

[8] Micaela Kaplan, How Model Context Protocol Connects LLMs to the Real World, Label Studio. [Online]. Available: https://labelstud.io/blog/how-model-context-protocol-connects-llms-to-the-real-world/

[9] Manas Deepak Patil, and Virag Vijay Lokhande, “Model Context Protocol MCP Enabling Scalable Ai Data Integration,” International Journal for Multidisciplinary Research, vol. 7, no. 2, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Aske Plaat et al., “Agentic Large Language Models, A Survey,” Journal of Artificial Intelligence Research, vol. 84, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Johannes Schneider, “Generative to Agentic AI: Survey, Conceptualization, and Challenges,” arXiv:2504.18875, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Deepak Bhaskar Acharya, Karthigeyan Kuppan, and B. Divya, “Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey,” IEEE Access, vol. 13, pp. 18912–18936, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Mourad Gridach et al., “Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions,” arXiv:2503.08979, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Ranjan Sapkota, Konstantinos I. Roumeliotis, and Manoj Karkee, “AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges,” Information Fusion, vol. 126, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Soodeh Hosseini, and Hossein Seilani, “The Role of Agentic AI in Shaping a Smart Future: A Systematic Review,” Array, vol. 26, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Baoyu Liang, Yuchen Wang, and Chao Tong, “AI Reasoning in Deep Learning Era: From Symbolic AI to Neural–Symbolic AI,” Mathematics, vol. 13, no. 11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] T. Nithya et al., “A Comprehensive Survey of Machine Learning: Advancements, Applications, and Challenges,” 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Thomas Rincy N, and Roopam Gupta, “A Survey on Machine Learning Approaches and Its Techniques,” 2020 IEEE International Students’ Conference on Electrical,Electronics and Computer Science (SCEECS), 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[19] William Grant Hatcher, and Wei Yu, “A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends,” IEEE Access, vol. 6, pp. 24411–24432, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Md Zahangir Alom et al., “A State-of-the-Art Survey on Deep Learning Theory and Architectures,” Electronics, vol. 8, no. 3, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Sandeep Singh Sengar et al., “Generative Artificial Intelligence: A Systematic Review and Applications,” Multimedia Tools and Applications, vol. 84, pp. 23661–23700, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Tam Sakirin, and Siddartha Kusuma, “A Survey of Generative Artificial Intelligence Techniques,” Babylonian Journal of Artificial Intelligence, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Francesco Piccialli et al., “AgentAI: A Comprehensive Survey on Autonomous Agents in Distributed AI for Industry 4.0,” Expert Systems with Applications, vol. 291, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Andreas Brännström et al., “A Formal Framework for Designing Boundedly Rational Agents,” Proceedings of the 14^th International Conference on Agents and Artificial Intelligence, vol. 3, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Prashant Gupta, Rational Agents for Artificial Intelligence, Medium, 2017. [Online]. Available: https://medium.com/hackernoon/rational-agents-for-artificial-intelligence-caf94af2cec5

[26] Laurent Frering, Gerald Steinbauer-Wagner, and Andreas Holzinger, “Integrating Belief-Desire-Intention Agents with Large Language Models for Reliable Human–robot Interaction and Explainable Artificial Intelligence,” Engineering Applications of Artificial Intelligence, vol. 141, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Geylani Kardas, Baris Tekin Tezel, and Moharram Challenger, “Domain-specific Modelling Language for Belief–Desire–Intention Software Agents,” IET Software, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Diego Aineto, Sergio Jiménez, and Eva “Learning STRIPS Action Models with Classical Planning,” arXiv:1903.01153, 2019.
[CrossRef] [Publisher Link]

[29] Xenija Neufeld, Sanaz Mostaghim, and Sandy Brand, “A Hybrid Approach to Planning and Execution in Dynamic Environments Through Hierarchical Task Networks and Behavior Trees,” Fourteenth Artificial Intelligence and Interative Digital Entertainment Conference, vol. 14, no. 1, pp. 201–207, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Sofia Kouah et al., “Internet of Things-Based Multi-Agent System for the Control of Smart Street Lighting,” Electronics, vol. 13, no. 18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Jiaxin Liang et al., “A Review of Multi-Agent Reinforcement Learning Algorithms,” Electronics, vol. 14, no. 4, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Shuo Yang et al., “Reinforcement Learning Agents Playing Ticket to Ride–A Complex Imperfect Information Board Game With Delayed Rewards,” IEEE Access, vol. 11, pp. 60737–60757, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Ajay Bandi et al., “The Rise of Agentic AI : A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges,” Future Internet, vol. 17, no. 9, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Markets and Markets, AI Agents Market Size, Share, Growth and Lates Trends, 2025. [Online]. Available: https://www.marketsandmarkets.com/Market-Reports/ai-agents-market-15761548.html

[35] AI Agents Market (2026 - 2033), Grand View Research. [Online]. Available: https://www.grandviewresearch.com/industry-analysis/ai-agents-market-report

[36] Venus Garg, “Designing the Mind: How Agentic Frameworks Are Shaping the Future of AI Behavior,” Journal of Computer Science and Technology Studies, vol. 7, no. 5, pp. 182–193, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Mohammed Salah et al., “Agentic Artificial Intelligence in Public Administration: Foundations, Applications, and Governance Mohammed Salah,” SSRN, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[38] Yi Yu et al., “Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents,” arXiv: 2601.01885, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[39] Gokcer Belgusen, Memory Types in Agentic AI: A Breakdown, Medium, 2025. [Online]. Available: https://medium.com/@gokcerbelgusen/memory-types-in-agentic-ai-a-breakdown-523c980921ec

[40] Mohan Varthakavi, Reimagining Data Architecture for Agentic AI, DataVarsity, 2025. [Online]. Available: https://www.dataversity.net/articles/reimagining-data-architecture-for-agentic-ai/#:~:text=would%20likely%20miss.-

[41] Manish Sood, “Agentic AI is Forcing a Shift from Application-first to Data-first Architecture, RELTIO, 2026. [Online]. Available: https://www.reltio.com/resources/blog/agentic-ai-is-forcing-a-shift-from-application-first-to-data-first-architecture/#:~:text=It

[42] Xinyi Hou et al., “Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions,” ACM Transactions of Software Engineering and Methodology, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[43] Anna Gutowska, What is Model Context Protocol (MCP)?, IBM. [Online]. Available: https://www.ibm.com/think/topics/model-context-protocol

[44] Padmanabhan Venkiteela, “The New Interoperability Paradigm : Model Context Protocol ( MCP ), APIs, and the Future of Agentic AI,” Computer Fraud and Security, vol. 2025, no. 1, pp. 1259–1271, 2025.
[Google Scholar] [Publisher Link]

[45] Aniket P. Kakde et al., “Advancing Agentic AI through Communication Protocols,” International Journal of Scientific Research in Science and Technology, vol. 12, no. 5, pp. 299–308, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[46] Manoj Kumar Rath, “Adaptive Model Context Protocols for Trustworthy and Secure Agentic AI Systems,” International Journal of Computer Technology and Electronics Communication, vol. 8, no. 5, pp. 11444–11456, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[47] Codiste, Model Context Protocol (MCP) vs Traditional APIs: Key Differences and Use Cases, Medium. [Online]. Available: https://medium.com/@nishantbj/model-context-protocol-mcp-vs-traditional-apis-key-differences-and-use-cases-24dc023f16f2

[48] Herman Errico, Jiquan Ngiam, and Shanita Sojan, “Securing the Model Context Protocol (MCP): Risks, Controls, and Governance,” arXiv: 2511.20920, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[49] Sonu Kumar et al., “MCP Guardian: A Security-First Layer for Safeguarding MCP-Based AI,” Computer Science and Information Technology, pp. 107–121, 2025.
[CrossRef] [Publisher Link]

[50] Grigoris Ntousakis et al., “Securing MCP-Based Agent Workflows,” Proceedings of the 4^th Workshop on Practical Adoption Challenges of ML for Systems, pp. 50-55, 2025.
[CrossRef] [Google Scholar] [Publisher Link]