DOI: https://doi.org/10.14710/jmasif.16.2.77084

A Critical Review of Agentic AI: Core Technologies, Applications, Ethical Implications, and Future Research Directions

Strategic Markets, Kyndryl, India

Received: 18 Aug 2025; Revised: 19 Oct 2025; Accepted: 24 Oct 2025; Available online: 5 Nov 2025.
Open Access Copyright (c) 2025 The authors. Published by Department of Informatics Universitas, Diponegoro
Creative Commons License This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Citation Format:
Abstract

Artificial intelligence (AI) is progressing toward the Agentic AI paradigm, which involves intelligent systems capable of autonomous, proactive, and goal-focused behavior through adaptive interactions with their environment. This article offers a critical review of the development of Agentic AI by analyzing its technological foundations, application areas, and the associated technical, ethical, and policy challenges. The review adopts a narrative approach by examining primary literature from the IEEE, Scopus, and ScienceDirect databases for 2019–2025 using keywords such as agentic AI, multi-agent systems, human–AI collaboration, and autonomous decision systems. The findings are organized into a three-layer conceptual framework linking core technologies like Reinforcement Learning, Multi-Agent Systems, and Natural Language Processing with various application domains and cross-cutting challenges. The analysis indicates that despite the significant potential of Agentic AI, gaps remain in areas such as agent interoperability, autonomy assessment metrics, and field implementation limitations. This article proposes a structured research agenda aimed at developing Agentic AI that is more transparent, trustworthy, and aligned with human values.

Fulltext
Keywords: Agentic AI, Generative AI, Artificial Intelligence, Cloud Computing , Machine Learning

Article Metrics:

Article Info
Section: Review Article
Language : EN
Recent articles
Performance Analysis Cryptography Using AES-128 and Key Encryption Based on MD5 An Efficient Bidirectional Gated Recurrent Unit Approach for Student Study Duration Modeling and Timely Graduation Forecasting A Comparative Analysis of the CRITIC and Entropy Methods for Objective Weighting of Priority Criteria A Critical Review of Agentic AI: Core Technologies, Applications, Ethical Implications, and Future Research Directions More recent articles
Most cited articles
KLASIFIKASI UCAPAN KATA DENGAN SUPPORT VECTOR MACHINE PENYELESAIAN MASALAH JOB SHOP MENGGUNAKAN ALGORITMA GENETIKA Pengenalan Jenis Golongan Darah Menggunakan Jaringan Syaraf Tiruan Perceptron APLIKASI SISTEM INFORMASI GEOGRAFIS BERBASIS WEB PENYEBARAN DANA BANTUAN OPERASIONAL SEKOLAH Enterprise Architecture Model untuk Aplikasi Government More cited articles
  1. S. Goyal and G.K. Goyal, “Artificial Neural Network Simulated Elman Models for Predicting Shelf Life of Processed Cheese". Int. J. of App. Metaheur. Comp., Vol.3, No.3, pp.20-32, 2012. https://doi.org/10.4018/jamc.2012070102
  2. S. Goyal, “Artificial Neural Networks in Fruits: A Comprehensive Review”. Int. J.of Image, Grap. and Sig. Process.,Vol.6, No.5, pp. 53, 2014. https://doi.org/10.5815/ijigsp.2014.05.07
  3. R. Kaur, D. Gabrijelčič, and T. Klobučar, “Artificial intelligence for cybersecurity: Literature review and future research directions”, Info. Fusion, Vol.97, pp. 101804, 2023. doi: https://doi.org/10.1016/j.inffus.2023.101804
  4. S. Latif, F. Shamshad, H. S. Ali, F. Pervez, E. Cambria, and H. Cuayáhuitl, “A survey on deep reinforcement learning for audio-based applications”, Artificial Intelligence Review, Vol. 56, No. 3, pp. 2193–2240, 2022. https://doi.org/10.1007/s10462-022-10224-2
  5. S. Mo, X. Pei, and C. Wu, “Safe reinforcement learning for autonomous vehicle using Monte Carlo tree search”, IEEE Transactions on Intelligent Transportation Systems, Vol. 23, No. 7, pp. 6766–6773, 2022. https://doi.org/10.1109/tits.2021.3061627
  6. M. M. Karim, Q. Qu, D. H. Van, S. Khan, and Y. Kholodov, “AI agents meet blockchain: A survey on secure and scalable collaboration for multi-agents”, Future Internet, Vol. 17, No. 2, p. 57, 2025. https://doi.org/10.3390/fi17020057
  7. N. Bougueroua, A. Derhab, S. Mazouzi, M. Belaoued, N. Seddari, and A. Bouras, “A survey on multi-agent based collaborative intrusion detection systems”, Journal of Artificial Intelligence and Soft Computing Research, Vol. 11, No. 2, pp. 111–142, 2021. https://doi.org/10.2478/jaiscr-2021-0008
  8. P. Hitzler, A. Eberhart, M. Ebrahimi, M. K. Sarker, and L. Zhou, “Neuro-symbolic approaches in artificial intelligence”, National Science Review, Vol. 9, No. 6, 2022. https://doi.org/10.1093/nsr/nwac035
  9. R. Sajja, M. Cikmaz, D. Cwiertny, Y. Sermet, and I. Demir, “Artificial intelligence-enabled intelligent assistant for personalized and adaptive learning in higher education”, Information, Vol. 15, No. 10, p. 596, 2024. https://doi.org/10.3390/info15100596
  10. T. Taniguchi, H. Yamakawa, T. Nagai, K. Doya, M. Sakagami, M. Suzuki, T. Nakamura, and A. Taniguchi, “A whole brain probabilistic generative model: Toward realizing cognitive architectures for developmental robots”, Neural Networks, Vol. 150, pp. 293–312, 2022. https://doi.org/10.1016/j.neunet.2022.02.026
  11. P. Radanliev, “Artificial intelligence: Reflecting on the past and looking towards the next paradigm shift”, Journal of Experimental & Theoretical Artificial Intelligence, Vol. 37, No. 7, pp. 1045–1062, 2024. https://doi.org/10.1080/0952813x.2024.2323042
  12. L. W. Y. Yang, X. Lei, X. Zhang, M. Yan, Y. Liu, D. S. W. Ting, L. L. Foo, and W. Y. Ng, “Deep learning-based natural language processing in ophthalmology: Applications, challenges and future directions”, Current Opinion in Ophthalmology, Vol. 32, No. 5, pp. 397–405, 2021. https://doi.org/10.1097/icu.0000000000000789
  13. Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57(4). https://doi.org/10.1007/s10462-024-10721-6
  14. E. Dilek and M. Dener, “Computer vision applications in intelligent transportation systems: A survey”, Sensors (Basel, Switzerland), Vol. 23, No. 6, p. 2938, 2023. https://doi.org/10.3390/s23062938
  15. R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction”, MIT Press, 2018. https://doi.org/10.1016/S0893-6080(99)000982
  16. J. Chen, "Generative AI for Social Engineering Attack Simulation," IEEE Trans. Inf. Forensics and Sec., Vol.16, pp. 4871-4883, 2021. https://doi.org/10.13140/RG.2.2.19118.32326
  17. N. Bougueroua, S. Mazouzi, S. Belaoued, N. Seddari, A. Derhab, and A. Bouras, “A survey on multi-agent based collaborative intrusion detection systems”, J. of A. I. and Soft Comp. Res., Vol.11, No.2, pp. 111-142, 2021 https://doi.org/10.2478/jaiscr-2021-0008
  18. A. O. Hashesh, M. M. Fouda, R. M. Zaki, S. Hashima, K. Hatano, and A. S. T. Eldien, “AI-enabled UAV communications: Challenges and future directions”, IEEE Access, Vol. 10, pp. 92048–92066, 2022. https://doi.org/10.1109/access.2022.3202956
  19. L. Hughes, Y. K. Dwivedi, T. Malik, M. Shawosh, M. A. Albashrawi, I. Jeon, V. Dutot, M. Appanderanda, T. Crick, R. De’, M. Fenwick, S. M. Gunaratnege, P. Jurcys, A. K. Kar, N. Kshetri, K. Li, S. Mutasa, S. Samothrakis, M. Wade, and P. Walton, “AI agents and agentic systems: A multi-expert analysis”, Journal of Computer Information Systems, Vol. 65, No. 4, pp. 489–517, 2025. https://doi.org/10.1080/08874417.2025.2483832
  20. D. Gupta, “Generative AI and Deep fakes: Ethical Implications and Detection Techniques”, J. of Sci., Tech. and Engg. Res., Vol.1, No.1, pp. 45-56, 2024. https://doi.org/10.64206/21rgkc40
  21. T. Ha, T.K. Dang, H. Le and T.A. Truong, “Security And Privacy Issues in Deep Learning: A Brief Review. SN Computer Science”, Vol.1, No.5, pp. 253, 2020. https://doi.org/10.1007/s42979-020-00254-4
  22. S. H. Thorat, “Agentic AI for Customer Service and Contact Center Solutions”. J. of Com. Science and Tech. Stud.”, Vol.7, No.8, pp. 444-451, 2025. https://doi.org/10.32996/jcsts.2025.7.8.49
  23. Y. Zhang and K. Siau, “Meta-entrepreneurship: An Analysis Theory On Integrating Generative AI, agentic AI, and metaverse for entrepreneurship”. J. of G. Info. Mgmt., Vol. 32, No. 1, pp.1-21, 2024. https://doi.org/10.4018/JGIM.364094
  24. U.M. Borghoff, P. Bottoni and R. Pareschi, “Human-Artificial Interaction In The Age of Agentic AI: a system-theoretical approach”. Fron. in Hum. Dyn., Vol. 7, pp. 1579166, 2025. https://doi.org/10.3389/fhumd.2025.1579166
  25. S. Sivakumar, “Agentic AI in predictive AIOPs: Enhancing It Autonomy and Performance. Int. J. of Sci. Res. and Mgmt., Vol. 12, No. 11, pp. 1631-1638, 2024 https://doi.org/10.18535/ijsrm/v12i11.ec01
  26. C. Chawla, S. Chatterjee, S.S. Gadadinni, P. Verma, and S. Banerjee, “Agentic AI: The building blocks of sophisticated AI business applications,” J. of AI, Rob. & Workp. Auto, Vol. 3, No.3, pp.1-15, 2024. https://doi.org/10.69554/XEHZ1946
  27. I. D. S Portugal, P. Alencar and D. Cowan, D., “An Agentic AI-Based Multi-Agent Framework For Recommender Systems. In IEEE Int. Conf. on Big Data, pp. 5375-5382, 2024. IEEE. https://doi.org/10.1109/BigData62323.2024.10825765
  28. V. Shankar, “Managing The Twin Faces of AI: A Commentary on “Is AI Changing The World For Better or Worse?”. J. of Macromark., Vol. 44, No.4, pp. 892-899, 2024. https://doi.org/10.1177/02761467241286483
  29. A.B. Arrieta, N. Díaz-Rodríguez, J.D. Ser, A. Bennetot, S. Tabik, A. Barbado, S. Garcia, S. Gil-Lopez, D. Molina, R. Benjamins, R. Chatila, F. Herrera, “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities And Challenges Toward Responsible AI”, Info. Fusion, Vol. 58, pp. 82-115, 2020. https://doi.org/10.1016/j.inffus.2019.12.012
  30. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair and Y. Bengio, “Generative adversarial nets”, Adv. in Neural Info. Process. Sys., Vol. 27, pp. 1-9, 2014. https://doi.org/10.1145/3422622
  31. V. Garg, “Designing the Mind: How Agentic Frameworks Are Shaping the Future of AI Behavior”, J. of Comp. Sci. and Tech. Stud., Vol.7, No.5, pp. 182-193, 2023. https://doi.org/10.32996/jcsts.2025.7.5.24
  32. Y. Tu, J. Chen and C. Huang, “Empowering personalized learning with generative artificial intelligence: Mechanisms, challenges and pathways”, Fron. of Digital Edu., Vol.2, No. 2, pp. 1-18, 2025. https://doi.org/10.1007/s44366-025-0056-9
  33. T. Miller, “Explanation In Artificial Intelligence: Insights From The Social Sciences”, Art. Intel., Vol. 267, pp. 1-38, 2019. https://doi.org/10.1016/j.artint.2018.07.007
  34. H. F. Rashvand, K. Salah, J.M.A. Calero and L. Harn, “Distributed Security For Multi-Agent Systems–Review And Applications”, IET Info. Sec., Vol. 4, No.4, pp. 188-201, 2010. https://doi.org/10.1049/iet-ifs.2010.0041
  35. C. Yinka-Banjo and O..A. Ugot, “A Review of Generative Adversarial Networks and Its Application In Cybersecurity. Art. Intel. R.”, Vol. 53, No. 3, pp. 1721-1736, 2020. https://doi.org/10.1007/s10462-019-09717-4
  36. D. Cohen, D. Te’eni, I. Yahav, A. Zagalsky, D. Schwartz, G. Silverman and J. Makowski, “Human–AI Enhancement of Cyber Threat Intelligence”, Int. J. of Info. Sec., Vol. 24, No. 2, pp. 99, 2025. https://doi.org/10.1007/s10207-025-01004-4
  37. D. Cohen, D. Te’eni, I. Yahav, A. Zagalsky, D. Schwartz, G. Silverman and J. Makowski, “Human–AI Enhancement of Cyber Threat Intelligence”, Int. J. of Info. Sec., Vol. 24, No. 2, pp. 99, 2025. https://doi.org/10.1007/s10207-025-01004-4
  38. L. Hughes, Y.K. Dwivedi, T. Malik, M. Shawosh, M.A. Albashrawi, I. Jeon, V. Dutot, M. Appanderanda, T. Crick, R. De’, M. Fenwick, “AI agents and agentic systems: A multi-expert analysis”, J. of Comp. Info. Sys., Vol. 26, pp. 1-29, 2025. https://doi.org/10.1080/1097198X.2025.2524286
  39. B. Zyoud and S.L. Lutfi, “Adapting Zero Trust: Information Security Cultural Factors Considerations in the UAE Context”, Asia-Pac. J. of Info. Tech. & Mul., Vol. 13, No. 2, 2024. https://doi.org/10.17576/apjitm-2024-1302-09
  40. I. H. Sarker, M.H. Furhad and R. Nowrozy, “AI-driven cybersecurity: an overview, security intelligence modeling and research directions”, SN Comp. Sci., Vol. 2, No. 3, pp.173, 2021. https://doi.org/10.1007/s42979-021-00557-0
  41. N. Papernot, "Practical Black-Box Attacks against Machine Learning," In Proc. ACM Asia Conf. on Comp. and Comm. Sec., 2017. https://doi.org/10.1145/3052973.30530
  42. L. Wang, "Autonomous Security Operations Centers: A Case Study," In Proc. IEEE Conf. on Comm. and Net. Sec., pp. 550-561, 2022. https://doi.org/10.63282/3050-922X.IJERET-V6I2P108
  43. V. Kumar and D.Sinha, “Synthetic attack data generation model applying generative adversarial network for intrusion Detection”, Comp. & Sec, Vol. 125, pp. 103054, 2023. https://doi.org/10.1016/j.cose.2022.103054

Last update:

No citation recorded.

Last update: 2025-11-05 09:17:10

No citation recorded.