A Research Landscape of Agentic AI and Large Language Models: Applications, Challenges and Future Directions
Open accessThe DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
Abstract
Agentic AI and Large Language Models (LLMs) are transforming how language is understood and generated while reshaping decision-making, automation, and research practices. LLMs provide underlying reasoning capabilities, and Agentic AI systems use them to perform tasks through interactions with external tools, services, and Application Programming Interfaces (APIs). Based on a structured scoping review and thematic analysis, this study identifies that core challenges of LLMs, relating to security, privacy and trust, misinformation, misuse and bias, energy consumption, transparency and explainability, and value alignment, can propagate into Agentic AI. Beyond these inherited concerns, Agentic AI introduces new challenges, including context management, security, privacy and trust, goal misalignment, opaque decision-making, limited human oversight, multi-agent coordination, ethical and legal accountability, and long-term safety. We analyse the applications of Agentic AI powered by LLMs across six domains: education, healthcare, cybersecurity, autonomous vehicles, e-commerce, and customer service, to reveal their real-world impact. Furthermore, we demonstrate some LLM limitations using DeepSeek-R1 and GPT-4o. To the best of our knowledge, this is the first comprehensive study to integrate the challenges and applications of LLMs and Agentic AI within a single forward-looking research landscape that promotes interdisciplinary research and responsible advancement of this emerging field.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Privacy and data security risks | Inter-agent communication requires frequent sharing of sensitive patient data across distributed components, increasing attack surfaces and audit complexity (24, 45, 46, 48).”
From Ethical issues in multi-agent AI systems for healthcare: a narrative review (2026) · cites this paper as [24]
In the citing paper
“Erosion of human oversight and control | Multi-agent systems operate with goal-directed autonomy, negotiating and executing tasks with limited real-time human intervention (24, 26).”
From Ethical issues in multi-agent AI systems for healthcare: a narrative review (2026) · cites this paper as [24]
In the citing paper
“While these features improve operational efficiency, they also allow systems to act adaptively and self-correct without explicit human intervention, thereby displacing the clinician's central role in directing the system's trajectory.”
From Ethical issues in multi-agent AI systems for healthcare: a narrative review (2026) · cites this paper as [24]
In the citing paper
“(4) erosion of human oversight, as multi-agent AI systems operate beyond effective human control;”
From Ethical issues in multi-agent AI systems for healthcare: a narrative review (2026) · cites this paper as [24]
In the citing paper
“(5) privacy and data security risks, stemming from complex data flows among agents;”
From Ethical issues in multi-agent AI systems for healthcare: a narrative review (2026) · cites this paper as [24]
8 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 4,254
A large language model for electronic health records
Yang, X., Chen, A., PourNejatian, N., Shin, H. C., Smith, K. E., Parisien, C., Compas, C., Martin, C., Costa, A. B., Flores, M. G., et al. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00742-2 · Cited by 847 · cited 1×
“The growing volume of imaging data and the complexity of EHRs can overwhelm clinicians, but LLMs help alleviate this burden, reducing cognitive load and enhancing patient safety efficiently [28,29].”
Agentic AI: Autonomous intelligence for complex goals–a comprehensive survey
Acharya, D. B., Kuppan, K., & Divya, B. (2025) · IEEE Access · doi:10.1109/access.2025.3532853 · Cited by 717 · cited 1×
“This issue often arises when goals are under-specified, ambiguous, or interpreted differently by the agent due to its internal representations or learned priors [6,21].”
Explainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681 · cited 1×
“In another study, Zhao et al. (2024) [76] provided a broader review of explainability techniques applied to LLMs.”
Security and Privacy Challenges of Large Language Models: A Survey
Das, B. C., Amini, M. H., & Wu, Y. (2025) · ACM Computing Surveys · doi:10.1145/3712001 · Cited by 445
Power Hungry Processing: Watts Driving the Cost of AI Deployment?
Luccioni, S., Jernite, Y., & Strubell, E. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658542 · Cited by 392 · cited 1×
“As these models are increasingly used in everyday applications such as search engines and customer service tools, the combined energy demand of repeated inference has become a significant challenge in the pursuit of more sustainable AI systems [66].”
Cultural bias and cultural alignment of large language models
Tao, Y., Viberg, O., Baker, R. S., & Kizilcec, R. F. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae346 · Cited by 383 · cited 1×
“As LLMs continue to advance in autonomy and decision-making, it becomes increasingly essential for them to align with human values, societal expectations, and ethical principles [68–71].”
Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
Tian, S., Jin, Q., Yeganova, L., Lai, P.-T., Zhu, Q., Chen, X., Yang, Y., Chen, Q., Kim, W., Comeau, D. C., et al. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad493 · Cited by 359 · cited 1×
“Their accelerated evolution is reshaping the way language is processed, knowledge is retrieved, and tasks are automated across various domains [1–4].”
Zhou, J., Zhang, Y., Luo, Q., Parker, A. G., & De Choudhury, M. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581318 · Cited by 288
The role of agentic AI in shaping a smart future: A systematic review
Hosseini, S., & Seilani, H. (2025) · Array · doi:10.1016/j.array.2025.100399 · Cited by 280 · cited 1×
“To address this, researchers need to create explainable agents [80] that utilise explain-able autonomy techniques, allowing agents to provide human-understandable justifications for their actions.”
Research works printed but not linked: 18
- Naveed, H., Khan, A.U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N., and Mian, A. (2023). A Comprehensive Overview of Large Language Models. arXiv.
- Xiao, Y., Shi, G., and Zhang, P. (2025). Towards Agentic AI Networking in 6G: A Generative Foundation Model-as-Agent Approach. arXiv.
- Wu, J., Zhu, J., and Liu, Y. (2025). Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research. arXiv.
- Gridach, M., Nanavati, J., Abidine, K.Z., Mendes, L., and Mack, C. (2025). Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions. arXiv.
- Jiang, F., Pan, C., Dong, L., Wang, K., Dobre, O.A., and Debbah, M. (2025). From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications. arXiv.
- Schneider, J. (2025). Generative to Agentic AI: Survey, Conceptualization, and Challenges. arXiv.
- Kamalov, F., Calonge, D.S., Smail, L., Azizov, D., Thadani, D.R., Kwong, T., and Atif, A. (2025). Evolution of ai in education: Agentic workflows. arXiv.
- Chu, Z., Wang, S., Xie, J., Zhu, T., Yan, Y., Ye, J., Zhong, A., Hu, X., Liang, J., and Yu, P.S. (2025). LLM Agents for Education: Advances and Applications. arXiv.
- Moor, M., Huang, Q., Wu, S., Yasunaga, M., Zakka, C., Dalmia, Y., Reis, E.P., Rajpurkar, P., and Leskovec, J. (2023). Med-Flamingo: A Multimodal Medical Few-shot Learner. arXiv.
- Cui, C., Ma, Y., Yang, Z., Zhou, Y., Liu, P., Lu, J., Li, L., Chen, Y., Panchal, J.H., and Abdelraouf, A. (2024). Large Language Models for Autonomous Driving (LLM4AD): Concept, Benchmark, Experiments, and Challenges. arXiv.
- Yang, G. (2025, April 05). Agentic AI: Service Operations with Augmentation and Automation AI. Available online: https://ssrn.com/abstract=5109470.
- Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., and Oprea, A. (2020). Extracting Training Data from Large Language Models. arXiv.
- Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L., Rothchild, D., So, D., Texier, M., and Dean, J. (2021). Carbon Emissions and Large Neural Network Training. arXiv.
- Shen, T., Jin, R., Huang, Y., Liu, C., Dong, W., Guo, Z., Wu, X., Liu, Y., and Xiong, D. (2023). Large Language Model Alignment: A Survey. arXiv.
- Turpin, A., Ma, X., Madaan, A., Lin, X., and Neubig, G. (2023). Language models do not explain themselves. arXiv.
- Shojaee, P., Mirzadeh, I., Alizadeh, K., Horton, M., Bengio, S., and Farajtabar, M. (2025). The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity. arXiv.
- Narajala, V.S., and Narayan, O. (2025). Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents. arXiv.
- Raza, S., Sapkota, R., Karkee, M., and Emmanouilidis, C. (2025). TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems. arXiv.
Cited by
Benchmarking large language model-based agent systems for clinical decision tasks
Liu, Y., Carrero, Z. I., Jiang, X., Ferber, D., Wölflein, G., Zhang, L., Jayabalan, S., Lenz, T., Hui, Z., & Kather, J. N. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02443-6 · Cited by 37
“We next evaluated the computational ef fi ciency of agent systems by assessing token usage and response times compared to baseline LLMs across multiple benchmarks.”
InfluentialExploring Agentic AI in Healthcare: A Study on Its Working Mechanism
Srinivasu, P. N., Kumari, G. L. A., Ahmed, S., & Alhumam, A. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2025.1753443 · Cited by 36
Goyez, J. P. L., González‐Briones, A., & Demazeau, Y. (2026) · Applied Sciences · doi:10.3390/app16031323 · Cited by 33
Vinay, V. (2026) · 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395809 · Cited by 15
“…are recorded with full transparency, including which schema/schemas, what parameters were retrieved, which data sources were used, and what results were returned, and this fits with enterprise audit requirements, incident-response documentation requirements, and regulatory controls [37], [38].”
Martinho, D., Sobreiro, P., Domingues, A., Martinho, F. I. F., & Nogueira, N. F. R. (2026) · Healthcare · doi:10.3390/healthcare14030287 · Cited by 23
Alamsabi, M., Tchuindjang, M., & Brohi, S. N. (2026) · Algorithms · doi:10.3390/a19010092 · Cited by 23
Self-citationAgentBound: Securing Execution Boundaries of AI Agents
Bühler, C., Biagiola, M., Di Grazia, L., & Salvaneschi, G. (2026) · Proceedings of the ACM on Software Engineering · doi:10.1145/3808103 · Cited by 9
Alqahtani, H., & Ahuja, P. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111184 · Cited by 12
Ethical issues in multi-agent AI systems for healthcare: a narrative review
Xie, Z., Wang, H., Dai, L., Wang, Z., Song, H., & Qian, J. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1792627 · Cited by 11
“Without such safeguards, error propagation in multi-agent healthcare systems risks producing clinically significant harms for which responsibility cannot be clearly assigned, leaving patients, clinicians, and institutions without effective mechanisms for redress or accountability (24).”
InfluentialJiang, Z., Xu, W., & Dong, B. (2026) · Advances in Applied Energy · doi:10.1016/j.adapen.2026.100273 · Cited by 9
Tian, Y., Jiang, Y., Jiang, Y., & Mrzljak, V. (2026) · Buildings · doi:10.3390/buildings16132569 · Cited by 6
Foundations of Agentic AI Redefining Autonomy in Learning Environments
Makhmudov, S., Maqsood, M., Musaev, U., Urazmetov, M., & Shahzadi, A. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4621-2.ch001 · Cited by 5
Exploring the Impact of AI Tools on Cognitive Skills: A Comparative Analysis
Musazade, N., Mezei, J., & Wang, X. (2025) · Algorithms · doi:10.3390/a18100631 · Cited by 10
“A recent survey emphasizes that LLMs alter the way people process information, evaluate trust, and engage with decision making, which parallels our observation that AI use systematically shifts the balance between analytical structuring and creative or integrative reasoning [47].”
Agentic AI: a review, applications and open research challenges
Khalid, O., Farooqi, A. U. H., & Bilal, M. (2026) · Computing · doi:10.1007/s00607-026-01676-3 · Cited by 9
“Some also identified the core challenges of large language models (LLMs) [ 18 ].”
Agentic AI: A Perspective on Architecture, Frameworks and Applications
Raghavendra, P., & Saikia, M. J. (2026) · AI · doi:10.3390/ai7060219 · Cited by 6
A Holistic Review of Agentic AI Frameworks, Applications, and Research Trajectories
Peykani, P., Ghanidel, S., Javadi-Sisi, I., Snåšel, V., & Mirjalili, S. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10675-8 · Cited by 7
“Examining the application spec - trum of Agentic AI not only provides a picture of the technical capabilities of this technology but also illustrates how it can fundamentally transform approaches to education, healthcare, manufacturing, communication, and human interaction [98, 99].”
Large Language Model Adoption: Systematic Review, Theoretical Frameworks, and Meta-Analytic Evidence
Achuthan, K., Kolil, V. K., Tang, K., & Raman, R. (2026) · Information · doi:10.3390/info17060615 · Cited by 4
Oncioiu, I., Priescu, I., Joița, D., Banu, G. S., & Priescu, C.-M. (2026) · Electronics · doi:10.3390/electronics15061206 · Cited by 2
Trad, F. S., & Chehab, A. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104834 · Cited by 3
Klot, M. H., Đorđević, M., Tsaramirsis, G., & Nassereddine, M. (2026) · IEEE International Multidisciplinary Conference on Engineering Technology (IMCET) · doi:10.1109/imcet69180.2026.11503692 · Cited by 2
Biswas, S. K., Mondal, R., & Saikia, M. J. (2026) · Future Internet · doi:10.3390/fi18080391 · Cited by 2
“Schneider [34] and Brohi et al. [38] highlight vulnerabilities such as prompt injection, adversarial tool manipulation, and multimodal jailbreak attacks.”
InfluentialAlgorithms have algorithm aversion
Guler, N., Cahalane, M. J., Kirshner, S., & Vidgen, R. T. (2026) · Industrial Management & Data Systems · doi:10.1108/imds-01-2025-0002 · Cited by 2
Phishing 2.0: exploring the capabilities and risks of agentic AI-enabled attacks
Chandre, P. R., Bhujbal, P., Kerketta, R., Nandimath, J., Shendkar, B. D., & Bhosale, R. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1795045 · Cited by 1
From simulation to learning: A comprehensive review of multi-agent systems in emergency management
Jin, X., Guo, T., Zhan, D., & Qi, C. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133841 · Cited by 1
Applications of DeepSeek in Medicine: Bibliometric Analysis and Scoping Review
Zhang, H., Wang, D., Xu, Y., Han, S., & Wang, G. (2026) · Journal of Medical Internet Research · doi:10.2196/93354 · Cited by 1
“Such limitations are particularly severe in domains involving rare diseases and complex, nonclassical clinical scenarios, where available pretraining data are often insufficient and clinically unvalida-ted [36,37,80,81].”
Toward Human-Centered Explanations for Agentic AI: Taxonomy, Mapping, and Evaluation
Hou, X., Mualla, Y., & Dridi, M. (2026) · International Conference on Human Centric Artificial Intelligence (ICHCAI) · doi:10.1109/ichcai70183.2026.11607607 · Cited by 2
“Third, the fluency-faithfulness gap in LLM-generated explanations has been noted [34] but not addressed in evaluation methodology: studies routinely measure explanation quality through metrics that cannot distinguish a well-grounded explanation from a confabulated one.”
Rezaei, Z., Amini, M. A., & Banad, Y. M. (2026) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2026.111859 · Cited by 1
Khan, Z. I. (2026) · doi:10.68708/jsrm.v1i1.02 · Cited by 1
“…rather than a single general-purpose agent handling the whole problem, the problem is divided into multiple subtasks and these subtasks are handled by multiple specialized agents that communicate, coordinate, negotiate or jointly reason to achieve common goals (Brohi et al., 2025; Li et al., 2024).”
Regulatory Frameworks for Agentic AI in Education
Evangeline, S. I. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4621-2.ch009
Agentic Metadata Cataloging for Power BI via LLM Scanners
Patlolla, M. R. (2026) · IEEE International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395862
Jiang, Z., Xu, W., & Dong, B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6353019
Gupta, R. D., Wei, L., Rahat, M. Y., Fahad, N., Ahmed, A., & Liew, T. H. (2025) · International Symposium on Artificial Intelligence and Big Data (AIBDF) · doi:10.1109/aibdf67964.2025.11440858
“Brohi et al. [11] further highlight that limitations of LLMs, including opaque decision-making and coordination challenges, propagate to agentic AI systems, motivating the need for robust multimodal frameworks for human behavior understanding.”
Corporate Communication, Agentic AI, and Prompt Injections
Langenbucher, K. C., & Bauer, K. (2026) · Oxford University Press eBooks · doi:10.1093/9780198945215.003.0141
Artificial Intelligence in Higher Education: Opportunities, Challenges, and Global Perspectives
Nazim, M., & Nazim, Z. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7097-2.ch003
Governing Autonomous Intelligence: Risks, Accountability, and Control in the Era of Agentic AIPreprint
Balodis, I. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6652900
Hong, X., & Huang, K. (2026) · Applied Sciences · doi:10.3390/app16094213
“However, the rapid rise in Generative AI and Large Language Models (LLMs) in 2023 [1] marks the entry of smart terminals into a new era of autonomous, AI-driven agents (“Agentic AI”) [5].”
Лобачев, М., & Шутов, С. (2026) · Наука і техніка сьогодні · doi:10.52058/2786-6025-2026-3(57)-2605-2618
Agentic AI and the Algorithm of Good
Gounaris, A., & Kosteletos, G. (2026) · AI · doi:10.3390/ai7090352
“…by increased autonomy [58,204–207]—for instance, in reasoning, planning, and code generation [208–210]—as well as by goal-directedness, learning capabilities, and adaptability [50,204,207,208], together with the capacity for novel emergent behaviours [204] and multi-agent cooperation [205,208,211].”
InfluentialOliveira, P., Pereira, J. D. C., & Nováis, P. (2026) · SpringerBriefs in intelligent systems · doi:10.1007/978-3-032-24781-0_7
Agentic AI Supporting Accounts Payable in Procurement
Nicoletti, B. (2026) · Springer eBooks · doi:10.1007/978-3-032-23024-9_9
AI-Driven Multi-agent Sustainable Shopping Companion: ECO Wise
Denge, O., Yashwardhan, W., Jadhav, T., Shinde, S., & Kulkarni, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-27160-0_18
Maria, I., & Barthos, M. (2026) · International Journal of Social Service and Research · doi:10.46799/ijssr.v6i5.1404
“AI developments are moving towards the use of Large Language Models (LLM), Agentic AI, and even the implementation of Physical AI has been initiated (Brohi et al., 2025; Buyya, 2026).”
The Human Experience of Algorithmic HR: A Design-Sensitive, Semi-Structured Review
Mizuki, I., & Khan, Z. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-2303-7.ch002 · Cited by 1
Strategic Embedding of Responsible AI: Governance Architecture and Hybrid Human–AI Value Creation
Tomminen, V., Leppäniemi, M., Kemppainen, T., & Frank, L. (2026) · Bled eConference · doi:10.18690/um.fov.4.2026.20
Cobb, M., & COGHLAN, S. (2026) · Frontiers in Animal Science · doi:10.3389/fanim.2026.1868726 · Cited by 1
Peng, C. (2026) · Ingegneria Sismica · doi:10.65102/is20261267
Kim, S.-Y., Park, S., Jeon, A., Jeong, Y.-R., 손규하, & Lee, I.-G. (2026) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom59046.2026.11571532 · Cited by 1
“…system that autonomously plans and executes actions to achieve a given objective, based on LLMs. Unlike conventional generative AI, which focuses on single-turn responses, agentic AI performs continuous decision-making through an iterative cycle of perception, planning, execution, and feedback [7].”
From Automation to Autonomy: The Role of Agentic AI in Industry 5.0
Srinivasu, P. N., Jose, A., Amer, A., Muda, Z. C., Madireddy, A., Chetana, V. L., Kumar, Y., & Ijaz, M. F. (2025) · Asian Conference on Communication and Networks (ASIANComNet) · doi:10.1109/asiancomnet68615.2025.11579681
“Consequently, the AAI configuration is stable, flexible, and ready for future challenges [10].”
Alam, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7665-3.ch012
Bridging the Blind Spots: A Holistic Risk Model for Secure Deployment of Large Language Models
Ozeri, Y. N., Schreiber, I., & Schreiber, A. (2026) · International Journal of Advanced Engineering and Management Research · doi:10.51505/ijaemr.2026.11333
Helmy, H., Rabah, C. B., & Serag, A. (2026) · AI · doi:10.3390/ai7070261 · Cited by 1
197Chapter 9 Describing the Various Types of LLM-Inspired Agents
Devi, S. C., Manjula, A., Niraimathi, R., & Karun, B. (2026) · De Gruyter eBooks · doi:10.1515/9783112223062-009
31Chapter 2 Architecture of Agentic AI Depicting the Core Components Involved
Rekha, M., Ravi, C., & Al-Zadjali, N. S. H. (2026) · De Gruyter eBooks · doi:10.1515/9783112223062-002
Agentic AI Unleashed: Power, Promise, and Ethical Frontiers
Wang, M., Wang, Y., & Ma, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3761-6_3
Explainable Agentic AI: Concepts, Scope, and Research Questions
Hou, X., Mualla, Y., & Dridi, M. (2026) · International Conference on Human-AI Interaction and Experience Design (HAXD) · doi:10.1109/haxd70072.2026.11620927 · Cited by 1
Omofoye, M. R., Awodele, O., Fabiyi, O. A., & Daniel, P. G. (2026) · Global Journal of Engineering and Technology Advances · doi:10.30574/gjeta.2026.28.2.0202
Nair, A. J., Manohar, S., & Rao, S. R. (2026) · Journal of Service Theory and Practice · doi:10.1108/jstp-10-2025-0420
Šindleryová, I. B., Chuťka, L., Turčan, K., & Machyniak, J. (2026) · Journal of Entrepreneurship and Sustainability Issues · doi:10.9770/p3545922549
Nothing new under the sun: Agentic AI and the automated, connected catalog
Darcy, N., Jansen, H. J., Burns, C. S., & Moulaison, H. L. (2026) · Technical Services Quarterly · doi:10.1080/07317131.2026.2719143
“For example, Brohi et al. (2025) demonstrate that across six domains including education, healthcare, and autonomous vehicles, LLM based agentic AIs inherit many of the challenges associated with non-agentic LLMs, including security concerns, mis-information, energy demands, and transparency gaps.”
Adaptive Ambiguity Reduction in Crop Disease Diagnosis via an LLM Agent
Ghommat, K., Bourkoukou, O., & Ouaarab, A. (2026) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc71566.2026.11650340
“Meanwhile, the agentic architecture supplies the body needed for sustained, goal-oriented operation in the real world [19], [20], [21], [22].”
Dai, S., & Zhang, J. (2026) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1145/3813822.3814116
Chabane, B., Abdul-Nour, G., & Komljenović, D. (2026) · Energies · doi:10.3390/en19174142
Agentic AI in Smart Higher Education: Building Adaptive, Human-Centered Learning Ecosystems
Salendab, F. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-4050-8.ch001
Beyond the autonomy illusion: hybrid intelligent systems and the architecture of AI accountability
Medsker, L., & Virmani, S. (2026) · AI and Ethics · doi:10.1007/s43681-026-01327-5
From Optimization to Autonomy: A Survey on Resource Allocation for Network Slicing in O-RAN
Gotseva, N., Ivanov, A., Vlahov, A., Poulkov, V. K., & Zaharis, Z. D. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3733812
“With the increasing complexity of these systems, further investigation is necessary to achieve scalable governance for multi-agent coordination and retain the autonomy of individual agents, especially in RT applications [89].”
InfluentialAgentic AI Frameworks for Autonomous Multi Agent Reasoning and Enterprise Decision Intelligence
Dommalapati, P. (2026) · International Conference Computational Vision and Bio Inspired Computing · doi:10.1109/iccvbic71195.2026.11689123
“This body of work argues that coordination evaluation must be a first-class subject for evaluating agentic systems for sensitive applications or applications with high stakes, along with task correctness [14].”
Albashrawi, M. A. (2026) · Information Discovery and Delivery · doi:10.1108/idd-09-2025-0235
AlYousef, M., Alrefaei, F., Almutairi, M., & Mohammed, A. (2026) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa70415.2026.11700342
“More recently, the emergence of AI agents [5] has introduced a new paradigm, where systems can autonomously perform complex tasks and make context-aware decisions.”
Foundation Models and Agentic AI for Autonomous Driving: A Systematic ReviewPreprint
Srinivaas, A., F, J. K., Ramasamy, L. K., Raju, G., Dhanaraj, R. K., & Urooj, S. (2026) · Research Square · doi:10.21203/rs.3.rs-10926683/v1
A systematic mapping study of AI agent–Tool communication: protocols, security, and orchestration
UMER, H. S., Nawaz, N. A. H., Ishaq, K., & Ahmad, A. (2026) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2026.200733
AI ethics in education: Integrating pedagogy, technology, and governance
KARAKUŞ, A. (2026) · Journal of Interdisciplinary Research in Artificial Intelligence and Society · doi:10.20897/jirais/19468
“For example, automated grading systems should be reviewed by teachers, ensuring that AI functions as a supportive tool rather than a replacement (Brohi et al., 2025; Dadson et al., 2025).”
Multi-Agent Architecture for Decision Support Systems in Agricultural Data Analysis
Musonip, M. L. R., Girinoto, Yuntanozra, M. D. K. H., & Zharfa, A. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715075
“Large Language Models (LLMs) have significantly enhanced conversational reasoning capabilities [6], [7], but direct use in analytical systems presents challenges including hallucination, unstructured reasoning, and limited execution control [8].”
AUTONOMOUS AI AGENTS AS DIGITAL EMPLOYEES IN ORGANIZATIONS: A SYSTEMATIC LITERATURE REVIEW
(2026) · Issues in Information Systems · doi:10.48009/3_iis_2026_117
Lee, S. (2026) · Discover Cities · doi:10.1007/s44327-026-00379-w
Pampel, J. R., Clauß, T., & Cesinger, B. (2026) · Zeitschrift für Klein- und Mittelunternehmen/Zeitschrift für KMU und Entrepreneurship · doi:10.3790/zfke.2026.1489101
An Autonomous Agent RAG Framework for Multimodal Customer Insights in E-commerce
Song, Y., Wang, L., Chen, J., Fan, X., Li, J., & Li, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38715-8_1
SecAgentSched: Secure agentic LLM scheduling for privacy-preserving UAV operations
Devaraj, R., Nair, P. P., Moulik, S., Kolady, J. V., & Sarma, R. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111598
Antara, F. (2026) · Southeast Symposium on Contemporary Engineering Topics (SSCET) · doi:10.1109/sscet69323.2026.11735558
Prasai, K. R. (2026) · NPRC Journal of Multidisciplinary Research. · doi:10.3126/nprcjmr.v3i10.100729
“Monitoring, certification, and audit mechanisms also remain underdeveloped, particularly for increasingly autonomous AI systems whose risks emerge through interactions among models, users, organizations, and institutional environments (Mittelstadt, 2019; Brohi et al., 2025).”
InfluentialAgentic AI and Autonomous LLM Systems: A Scientific Literature Review
Karthick, S., & Sherill, A. (2026) · International Journal of Creative and Open Research in Engineering and Management · doi:10.55041/ijcope.v2i10.194
Rathod, B., Baviskar, M. D., & Puri, S. (2026) · Drug Development Research · doi:10.1002/ddr.70400 · Cited by 1
Directions of enabling Agentic AI based Platforms: Digital Transformation with AI Strategy
Masuda, Y., Chuang, M. Y., Taylor, J., & Jain, R. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.10.372
Autonomous Vehicles with Digital Platforms: Digitization of Societies toward Ecosystem
Masuda, Y., Taylor, J., Chuang, M. Y., Toma, T., & Shirasaka, S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.10.378
Metadata
- Authors
- Brohi, S., Mastoi, Q.-U.-A., Jhanjhi, N. Z., & Pillai, T. R.
- Affiliations
- University of the West of England (GB)
- Taylor's University (MY)
- INTI International University (MY)
- Corresponding author
- Brohi, Sarfraz
- Venue
- Algorithms
- Publisher
- MDPI AG
- Published
- 2025-08-11
- Volume
- 18
- Issue
- 8
- Pages
- 499
- ISSN
- 1999-4893 (ISSN-L)
- OpenAlex
- W4413222071
- Cited by
- 69
- References
- 60
- Citations by year
- 2026: 64 · 2025: 5
- FWCI
- 71.12
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Algorithms (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- UWE Research Repository (UWE Bristol) (submittedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- agentic AI, large language models, LLM applications, privacy and security, trust, misinformation, bias, energy consumption, transparency and explainability, value alignment, goal misalignment, human oversight, multi-agent coordination, long-term safety, LLM limitations, DeepSeek-R1, GPT-4o, health care, cybersecurity, autonomous vehicles, e-commerce, customer service
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.