Evolution and Challenges of Agentic AI: From Autonomous Agents to Orchestrated Systems
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V4I3P119Keywords:
AI, Autonomous Agents, AI systems, Agentic AI, AI Governance, Ethical AI, Intelligent Automation, Distributed AI ArchitecturesAbstract
The Agentic Artificial Intelligence (AI) systems represent autonomous decision-making entities capable of collaboration, dynamic planning, and persistent memory, marking a significant evolution from classical AI agents. This paper provides a comprehensive survey of the conceptual evolution and architecture of agentic AI up to 2024, emphasizing transitions from isolated agents to orchestrated multi-agent systems. We explore core technical and ethical challenges, application domains such as business automation and robotics, and governance perspectives necessary for responsible deployment. Drawing insights from key foundational studies, reinforcement learning advances, and practical frameworks, the paper outlines open research directions critical for scalable, trustworthy agentic AI.
Downloads
References
[1] Arora, S., Nijssen, K., & Van Gucht, J. (2023). Advances in Multi-Agent Collaboration Strategies. Journal of Artificial Intelligence Research.
[2] Chan, L., Lopez, M., & Tan, S. (2024). Toward Scalable and Trustworthy Agentic AI Systems. Proceedings of the AAAI Conference on AI.
[3] Dhenia, R. N. K., Kanani, I. J., & Sridhar, I. J. R. (2023). Data Centric AI: Transforming the Future of Artificial Intelligence and Analytics. International Journal of Artificial Intelligence, Data Science, and Machine Learning.
[4] Kanani, I., Sridhar, R., & Dhenia, R. N. K. (2023). Security-Centric Artificial Intelligence: Strengthening Machine Learning Systems against Emerging Threats. International Journal of Artificial Intelligence and Data Science.
[5] Kwok, Y., Li, F., & Zhang, W. (2023). Orchestration Architectures for Multi-Agent Systems: A Survey. IEEE Transactions on Systems, Man, and Cybernetics.
[6] Levesque, H. J., & Lakemeyer, G. (2001). The Logic of Knowledge Bases. MIT Press.
[7] Lewis, P., Oguz, B., Rinott, R., Riedel, S., & Stoyanov, V. (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv preprint arXiv:2005.11401.
[8] Raghavendra Sridhar, I. J., Kumar Dhenia, R. N., & Kanani, I. J. (2021). Dynamic Frameworks for Enhancing Security in Digital Payment Systems. International Journal of Emerging Research in Engineering and Technology.
[9] Russell, S., & Norvig, P. (2009). Artificial Intelligence: A Modern Approach (3rd Ed.). Prentice Hall.
[10] Wooldridge, M. (2009). An Introduction to MultiAgent Systems. Wiley.
[11] Zhou, Q., Yang, Z., & Wang, J. (2022). Multi-Agent Reinforcement Learning: Algorithms and Applications. Journal of AI Research.
[12] Traverso, S., Mariani, L., & Mastrogiovanni, F. (2021). Cognitive Architectures for Autonomous Agents: Survey and Outlook. Cognitive Computation, 13(5), 1025–1051.
[13] Pan, S.J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
[14] Franklin, S., & Graesser, A. (1997). Is It an Agent, or Just a Program?: A Taxonomy for Autonomous Agents. Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages.
[15] Dignum, V. (2019). Responsible Artificial Intelligence: Designing AI for Human Values. IT - Information Technology, 61(6), 571–577.
[16] Jennings, N.R., Sycara, K., & Wooldridge, M. (1998). A Roadmap of Agent Research and Development. Autonomous Agents and Multi-Agent Systems, 1(1), 7–38.
[17] Pan, E., Lin, J., & Zhu, J. (2023). Towards Scalable Multi-Agent Reinforcement Learning with Hierarchical Coordination. AAAI Conference on Artificial Intelligence.
[18] Wooldridge, M. (2002). An Introduction to MultiAgent Systems. Wiley.
