Open Access
Subscription Access
Agentic AI: Autonomous Agents to Cognitive Autonomy
Abstract
Agentic Artificial Intelligence (Agentic AI) represents a paradigm shift from traditional rule-based and task-specific AI systems toward autonomous, goal-driven intelligent systems capable of reasoning, planning, and acting in dynamic environments. Unlike conventional AI agents that operate within predefined constraints, Agentic AI systems leverage foundation models, particularly large language models (LLMs), to achieve adaptive behavior, persistent memory utilization, and multi-agent coordination. This paper provides a comprehensive review of Agentic AI, covering its evolution from symbolic AI to modern generative and agent-based systems. Core architectural components, including perception, memory, planning, execution, and orchestration layers, are analyzed alongside prominent frameworks such as AutoGen, CrewAI, MetaGPT, LangGraph, and Semantic Kernel. A structured taxonomy of agentic systems is presented based on architecture, interaction paradigms, and domain specialization. The paper further examines enabling technologies such as reinforcement learning, multi-agent systems, and neurosymbolic AI, and discusses methodologies including BDI-based reasoning frameworks. Applications across healthcare, finance, manufacturing, and human–AI collaboration are explored to highlight practical impact. Finally, critical challenges including scalability, evaluation limitations, computational complexity, and ethical concerns are analyzed, followed by future research directions focusing on explainability, adaptive learning, and cross-domain generalization. This review aims to provide a coherent and analytical understanding of Agentic AI and its potential to redefine intelligent systems.
References
M. Abou Ali, F. Dornaika, and J. Charafeddine, “Agentic AI: A comprehensive survey of architectures, applications, and future directions,” Artif. Intell. Rev., vol. 59, no. 11, 2026, doi: 10.1007/s10462-025-11422-
A. Bandi, B. Kongari, R. Naguru, S. Pasnoor, and
S. V. Vilipala, “The rise of agentic AI: A review of definitions, frameworks, architectures, applications, evaluation metrics, and challenges,” Future Internet, vol. 17, no. 404, 2025, doi: 10.3390/fi17090404.
W. Olabiyi, D. Akinyele, and E. Joel, “The evolution of AI: From rule-based systems to data-driven intelligence,” 2025, unpublished.
J. Joshi, “The evolution of agentic AI: From rule-based systems to autonomous agents,” Int. J. Sci. Technol., vol. 16, no. 4, 2025, doi: 10.71097/IJSAT.v16.i4.5112.
M. Z. Alom, T. M. Taha, C. Yakopcic, S. Westberg, P. Sidike, M. S. Nasrin, B. C. Van Essen, A.
A. S. Awwal, and V. K. Asari, “The history began from AlexNet: A comprehensive survey on deep learning approaches,” 2018, arXiv:1803.01164. [Online]. Available: https://arxiv.org/abs/1803.01164
M. Al-Amin, M. S. Ali, A. Salam, A. Khan, A. Ali,
A. Ullah, M. N. Alam, and S. K. Chowdhury, “History of generative artificial intelligence (AI) chatbots: Past, present, and future development,” 2024, arXiv:2402.05122. [Online]. Available: https://arxiv.org/abs/2402.05122
Y. Yigit, M. A. Ferrag, M. C. Ghanem, I. H. Sarker, L. A. Maglaras, C. Chrysoulas, N. Moradpoor,
N. Tihanyi, and H. Janicke, “Generative AI and LLMs for critical infrastructure protection: Evaluation benchmarks, agentic AI, challenges, and opportunities,” Front. Comput. Sci., vol. 0, no. 0, pp. 1–42, 2025, doi: 10.1007/s11704-024-40231-1.
A. K. Pati, “Agentic AI: A comprehensive survey
of technologies, applications, and societal
implications,” IEEE Access, vol. 13, pp. 151824–151837, 2025, doi: 10.1109/ACCESS.2025.3585609.
Q. Wu, G. Bansal, J. Zhang, Y. Wu, S. Li, K. Zhu,
V. Peng, A. X. Liu, B. Zhang, and H. Wang, “AutoGen: Enabling next-gen LLM applications via multi-agent conversation,” 2023, arXiv:2308.08155. [Online]. Available: https://arxiv.org/abs/2308.08155
R. S. Sutton and A. G. Barto, Reinforcement learning: An introduction, 2nd ed. Cambridge, MA: MIT Press, 2018.
Refbacks
- There are currently no refbacks.