Agentic AI: Autonomous intelligence for complex goals–a comprehensive survey
Open accessThe DOI matches its Crossref record; 93 of the 93 references it cites were found in a registry or an index.
Abstract
Agentic AI, an emerging paradigm in artificial intelligence, refers to autonomous systems designed to pursue complex goals with minimal human intervention. Unlike traditional AI, which depends on structured instructions and close oversight, Agentic AI demonstrates adaptability, advanced decision-making capabilities and self-sufficiency, enabling it to operate dynamically in evolving environments. This survey thoroughly explores the foundational concepts, unique characteristics, and core methodologies driving the development of Agentic AI. We examine its current and potential applications across various fields, including healthcare, finance, and adaptive software systems, emphasizing the advantages of deploying agentic systems in real-world scenarios. The paper also addresses the ethical challenges posed by Agentic AI, proposing solutions for goal alignment, resource constraints, and environmental adaptability. We outline a framework for safely and effectively integrating Agentic AI into society, highlighting the need for further research on ethical considerations to ensure beneficial societal impacts. This survey serves as a comprehensive introduction to Agentic AI, guiding researchers, developers, and policymakers in engaging with its transformative potential responsibly and creatively.
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
“In contrast, Agentic AI systems are composed of multiple, specialized agents that coordinate, communicate, and dynamically allocate sub-tasks within a broader workflow to achieve a common goal(s) [22,44].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [22]
In the citing paper
“These shortcomings distinguish them from Agentic AI a recent paradigm that builds on deep learning, reinforcement learning, and foundation models to enable agents with contextual awareness, continuous learning, and emergent autonomy [22].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [22]
In the citing paper
“However, across these diverse systems, early AI agents shared common limitations: they lacked self-learning, generative reasoning, and adaptability to unstructured or evolving environments.”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [22]
In the citing paper
“Foundational AI Agents are typically composed of four primary subsystems: perception, reasoning, action, and learning.”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [22]
In the citing paper
“This emerging class of systems extends the capabilities of traditional AI Agents by enabling multiple intelligent entities to collaboratively pursue goals through structured communication [144-146], shared memory [147,148], and dynamic role assignment [22].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [22]
33 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-023-00834-7 · Cited by 2,267 · cited 1×
“The first is how Generative AI [8] works.”
XAI—Explainable artificial intelligence
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., & Yang, G.-Z. (2019) · Science Robotics · doi:10.1126/scirobotics.aay7120 · Cited by 2,053
Towards Personalized Federated Learning
Tan, A. Z., Yu, H., Cui, L., & Yang, Q. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3160699 · Cited by 1,182
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087
Human-in-the-loop machine learning: a state of the art
Mosqueira-Rey, E., Hernández-Pereira, E., Alonso-Ríos, D., Bobes-Bascarán, J., & Fernández-Leal, Á. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10246-w · Cited by 1,025
Rise of Machine Agency: A Framework for Studying the Psychology of Human–AI Interaction (HAII)
Sundar, S. S. (2020) · Journal of Computer-Mediated Communication · doi:10.1093/jcmc/zmz026 · Cited by 871
Collins, G. S., Dhiman, P., Andaur Navarro, C. L., Ma, J., Hooft, L., Reitsma, J. B., Logullo, P., Beam, A. L., Peng, L., Van Calster, B., et al. (2021) · BMJ Open · doi:10.1136/bmjopen-2020-048008 · Cited by 852 · cited 1×
“One such framework primarily employed is the risk evaluation and management protocol [64], which leads to the review of the risks posed by the actions of the AI, and subsequently, the control measures are put in place.”
Machine Learning in Predictive Maintenance towards Sustainable Smart Manufacturing in Industry 4.0
Çınar, Z. M., Abdussalam Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., & Safaei, B. (2020) · Sustainability · doi:10.3390/su12198211 · Cited by 834
Review of Image Classification Algorithms Based on Convolutional Neural Networks
Chen, L., Li, S., Bai, Q., Yang, J., Jiang, S., & Miao, Y. (2021) · Remote Sensing · doi:10.3390/rs13224712 · Cited by 789
A Survey on Curriculum Learning
Wang, X., Chen, Y., & Zhu, W. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3069908 · Cited by 692
Research works printed but not linked: 10
- Shavit, Practices for governing agentic ai systems, 1
- Yao, 2022, ReAct: Synergizing reasoning and acting in language models, arXiv:2210.03629 · arXiv
- Yang, GPT4Tools: Teaching large language model to use tools via self-instruction, 1
- Kong, 2021, Conversational AI With Rasa: Build, Test, and Deploy AI-powered, Enterprise-grade Virtual Assistants and Chatbots
- Tatineni, 2021, Ai-powered devops and mlops frameworks: Enhancing collaboration, automation, and scalability in machine learning pipelines, J. Artif. Intell. Res. Appl., 1, 58
- Pattyam, 2021, Artificial intelligence for healthcare diagnostics: Techniques for disease prediction, personalized treatment, and patient monitoring, J. Bioinf. Artif. Intell., 1, 309
- Pattyam, 2021, Ai-driven financial market analysis: Advanced techniques for stock price prediction, risk management, and automated trading, Afr. J. Artif. Intell. Sustain. Develop., 1, 100
- Johnson, 2020, Mimic-iv
- Miao, 2021, AI and Education: A Guidance for Policymakers
- Yanamala, 2022, Adaptive middleware framework for context-aware pervasive computing environments, Int. J. Mach. Learn. Res. Cybersecurity Artif. Intell., 13, 35
Cited by
Items 801–821 of 821
A Private Set Union Scheme for Privacy-Preserving Data Integration in Agentic AI Modeling
Kim, K., Lee, D. G., Kim, W., kim, S. H., & Lee, I. (2026) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2026.087619
Camilleri, M. A. (2026) · Business Strategy and the Environment · doi:10.1002/bse.71798
Agentic IoT for Urban Renewable Energy: A Conceptual Framework for Smart Cities
Guan, C., Shi, J., Yu, Y., & Zhou, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-0278-0.ch008
Multi-Agent Generative AI Framework for Adapting Syllabus and Personalizing Instruction
Guha, S., Ghosh, A., Singh, K. N., Misra, C., Mukul, M., & Sudershana, S. (2026) · doi:10.1109/click68749.2026.11742173
Aaesha Sultana, R., Basha, S. M., & Tabassum, N. (2026) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac70384.2026.11747268
Agentic AI and Multi-Agent Systems in Enterprise Communication and Automation
Misal, M., Chaudhari, A. Y., & Gaikwad, S. (2026) · International Conference on Information, Implementation, and Innovation in Technology (I2ITCON) · doi:10.1109/i2itcon69735.2026.11747903
Using edge computing and Large Language Models (LLM) for constructing a local agent
Prakosa, S. W., Rizal, N. A., & Kurniati, T. (2026) · JURNAL ELTEK · doi:10.33795/eltek.v24i2.11288
Agentic AI and Reinforcement Learning for Intelligent Software Development: A Systematic Review
Sindhu, B., & Janapati, R. (2026) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac70384.2026.11747663
Sustainable Agentic AI in Medicine: Toward Energy-Aware, Equitable, and Responsible Architectures
Barbato, L., & Gargiulo, F. (2026) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc70364.2026.11740098
Dixit, S. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-40490
URBANO, M. F. R., de Andrade, A. A., Facó, J. F. B., & da Silva, G. R. R. (2026) · International Journal of Advanced Engineering Research and Science · doi:10.22161/ijaers.13.10.3
FILLM: A Large Language Model Based Agentic System for Machine Learning Tabular Data Imputation
Gonçalves, C., Pereira, P., & Cortez, P. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.321
A preliminary design framework for human-friendly AI interaction: grounded in anthropomorphism
Jung, S., & Koo, Y. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1964763
Towards a Comprehensive Framework for Agentic AI Governance and Orchestration in Organizations
Ayadi, Y., Charroux, B., & Sliman, L. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.10.289
Ham, J.-H., Jung, H., Bae, S., & Kim, H. (2026) · Journal of Food Composition and Analysis · doi:10.1016/j.jfca.2026.109655
Multilayered Holistic AI Ecosystem Exploration and Trend Research
Majewski, M., & Czarnowski, I. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.10.169
A Conceptual Framework for Design Experience Consistency in Digital Business Ecosystems
Qin, R., Wang, S., & Zhao, D. (2026) · Systems · doi:10.3390/systems14111384
Autonomous Voice-Driven Multi-Agent Framework for Preference-Aware Product Discovery
Patil, M. K., Mohana Kumar, S., Naveen Kumar, B. K., & Chandrashekar, P. (2026) · International Conference on Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC) · doi:10.1109/icdscnc70670.2026.11746274
Measuring Autonomy in Agentic AI Systems
Gazala, V., & Elmi, S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.10.383
Improving Agentic AI Opportunity Identification Through GORE Driven Prompt Engineering
de Moraes, E. A., & Kalinowski, M. (2026) · doi:10.5753/se4as.2026.32414
Metadata
- Authors
- Acharya, D. B., Kuppan, K., & Divya, B.
- Affiliations
- University of Alabama in Huntsville (US)
- JPMorgan Chase & Co (United States) (US)
- Manipal Academy of Higher Education (IN)
- Venue
- IEEE Access
- Published
- 2025
- Volume
- 13
- Pages
- 18912-18936
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4406728221
- Cited by
- 717
- References
- 92
- Citations by year
- 2026: 492 · 2025: 225
- FWCI
- 287.59
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Keywords
- agentic AI, autonomous systems, goal pursuit, decision-making, self-sufficiency, adaptive software, medical applications, financial applications, AI ethics, goal alignment, resource constraints, environmental adaptability, social impact
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.