The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges
Open accessThe DOI matches its Crossref record; 136 of the 137 references it cites were found in a registry or an index, and 1 are not checked yet; 76 of the 457 sources its claims cite were checked for support.
Abstract
Agentic AI systems are a recently emerged and important approach that goes beyond traditional AI, generative AI, and autonomous systems by focusing on autonomy, adaptability, and goal-driven reasoning. This study provides a clear review of agentic AI systems by bringing together their definitions, frameworks, and architectures, and by comparing them with related areas like generative AI, autonomic computing, and multi-agent systems. To do this, we reviewed 143 primary studies on current LLM-based and non-LLM-driven agentic systems and examined how they support planning, memory, reflection, and goal pursuit. Furthermore, we classified architectural models, input–output mechanisms, and applications based on their task domains where agentic AI is applied, supported using tabular summaries that highlight real-world case studies. Evaluation metrics were classified as qualitative and quantitative measures, along with available testing methods of agentic AI systems to check the system’s performance and reliability. This study also highlights the main challenges and limitations of agentic AI, covering technical, architectural, coordination, ethical, and security issues. We organized the conceptual foundations, available tools, architectures, and evaluation metrics in this research, which defines a structured foundation for understanding and advancing agentic AI. These findings aim to help researchers and developers build better, clearer, and more adaptable systems that support responsible deployment in different domains.
Verified 2026-11-20 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This review synthesizes 143 primary studies to define agentic AI, compare it with generative AI, autonomic computing, and multi-agent systems, and map its frameworks, architectures, applications, input-output formats, evaluation metrics, and challenges. It reports rapid growth in 2024–2025 and identifies recurring architectural and evaluation approaches, while highlighting unresolved technical, coordination, ethical, and security limitations.
Key findings
- The review analyzed 143 primary studies; more than 90% were published in 2024 and 2025. Of these, 46% were peer-reviewed journals, 28% preprints, and 17% conference proceedings (methodology text).
- LLM-based frameworks such as LangChain, AutoGPT, BabyAGI, AutoGen, OpenAgents, CAMEL, MetaGPT, SuperAGI, and TB-CSPN enable planning, memory, reflection, tool use, and goal pursuit; non-LLM systems use rules (CLIPS, Drools, JADE), RL (Q-learning, DQN, policy gradients), planning (STRIPS/PDDL), and simulation (NetLogo, MASON).
- Five architectural models recur: ReAct single-agent, supervisor/hierarchical, hybrid reactive-deliberative, BDI, and layered neuro-symbolic; core components include perception, memory, planning, execution, reflection, orchestration, and interaction. Trade-offs include BDI explainability vs. brittleness, hierarchical scalability vs. supervisor bottlenecks, ReAct lightweight loops vs. limited parallelism, hybrid speed/planning vs. arbitration complexity, and neuro-symbolic uncertainty handling vs. integration overhead.
- Evaluation combines testing methods and qualitative/quantitative metrics. Reported examples include ~94% accuracy for LangGraph/CrewAI, 96% for Claude 3.5/LLaMa-3.2, 12 ± 2 min task completion time (34.2% improvement over traditional AI), and ~94% rule fidelity; challenges include 78% of organizations reporting data safety problems, plus architectural, tool-integration, coordination, human-AI interaction, ethical/governance, and security issues.
Methods
- Literature review/survey: searched Library Search, ACM Digital Library, ScienceDirect, Google Scholar, and Semantic Scholar with a query combining agentic AI/agent/autonomous AI/multiagent systems/autonomic computing/generative AI/AI planning/AI memory systems/AI feedback loops and survey/overview/review/summary/literature review terms; removed duplicates and screened abstracts/conclusions.
- Sample: 143 primary studies published from 2005 to present, with >90% from 2024–2025; also examined 21 survey/review articles across six dimensions using L/M/H/NA ratings.
- Analysis: extracted key information and synthesized definitions, frameworks, architectures, applications, input-output formats, evaluation metrics/testing methods, and challenges, using narrative synthesis and tabular summaries.
Limitations
- The paper does not state limitations of the review itself; it lists limitations/challenges of agentic AI systems: architectural/technical (dynamic task decomposition, hierarchical planning, adaptive reasoning, symbolic rigidity, long-term strategic planning, data volume/velocity/variety/veracity, opaque architectures), performance/tool integration (computational inefficiencies, lack of standard interfaces, limited design/test/deploy support), multi-agent coordination (communication, synchronization, scaling, correlated failures/collusion), human-AI interaction (limited transparency/interpretability, insecure interface design, misalignment with human intention), ethical/societal/governance (privacy/security risks; 78% of organizations reported data safety problems; accountability; communication failures; poor data quality), and security (adversarial attacks, data poisoning, misuse of tools/APIs, lack of oversight).
- Evident from the text: it is a narrative review without a stated formal quality appraisal, risk-of-bias assessment, or meta-analysis; no review-level limitations section is provided.
- Evident from the text: some reported publication counts appear inconsistent across sections (e.g., methodology text reports 32 arXiv, 27 conference proceedings, and 43 journal-based papers, while Table A2 reports 70 journals, 38 preprints, and 26 conference proceedings).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
56 Valid · 5 Not valid · 196 Not checked · 42 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Dynamic adaptation to changing environments and goals”
What the sources say
- Supportedcites [27] Joshi, 2025, Comprehensive Review of Artificial General Intelligence AGI and Agentic GenAI: Applications in Business and Finance, Int. J. Multidiscip. Res. Growth Eval. source
The paper’s Table 1 (following the Conclusion; page not provided) characterizes Agentic AI as goal-oriented and adaptive. The Technical Distinctions section also describes learning from environmental feedback, supporting the paraphrase that it adapts to changing environments and goals. (LLM, conf=0.85)
- Not checked — no full text of the sourcecites [41] Salah, M., Alnoor, A., Abdelfattah, F., and Al Halbusi, H. (2025, May 10). Agentic Artificial Intelligence in Public Administration: Foundations, Applications, and Governance. Applications, and Governance 2025. Available online: https://ssrn.com/abstract=5249100. source
- Not checked — no full text of the sourcecites [47] Acharya, 2025, Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey, IEEE Access source
- Not matchedcites [57] Raidas, M.A., and Bhandari, R. (2025). Agentic AI in Education: Redefining Learning for the Digital Era. Artificial Intelligence in EducationTransforming Learning for the Future, Scholars’ Press.
We searched by its title and found no matching paper.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The development of LLM-based frameworks like LangChain [26,31,78,80], AutoGPT [26,31,78], BabyAGI [31], AutoGen [80], and OpenAgents [26] shows a clear trend toward building smarter, more independent AI systems.”
What the sources say
- Partly supportedcites [26] Joshi, 2025, LLMOps, AgentOps, and MLOps for Generative AI: A Comprehensive Review, Int. J. Comput. Appl. Technol. Res. sourceExperimental — accuracy not yet measured
The conclusion describes growing complexity and independence in AI systems, and the 'Operationalizing Generative AI: From MLOps to AgentOps' section describes a shift toward autonomous, reasoning-driven agents. Those passages support the general trend, but our copy does not identify LangChain, AutoGPT, or BabyAGI as examples of it; searches for those names found no matching passage. Page numbers were not supplied for these sections. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [31] Shah, C., and White, R.W. (2024). Agents are not enough. arXiv. source
- Not matchedcites [78] Kalisetty, S., and Singireddy, J. (2023). Agentic AI in Retail: A Paradigm Shift in Autonomous Customer Interaction and Supply Chain Automation. Am. Adv. J. Emerg. Discip. (AAJED), 1.
We searched by its title and found no matching paper.
- Not matchedcites [80] Paleti, 2024, Agentic AI in Financial Decision-Making: Enhancing Customer Risk Profiling, Predictive Loan Approvals, and Automated Treasury Management in Modern Banking, Multidiscip. Sci. Work. Manag. J.
We searched by its title and found no matching paper.
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“A common integration pattern is a layered flow that couples components into an end-to-end decision loop: perception → world/state modeling → planning/reasoning → execution/tooling → evaluation/feedback → memory → (back to) planning.”
What the sources say
- Not checked — no full text of the sourcecites [41] Salah, M., Alnoor, A., Abdelfattah, F., and Al Halbusi, H. (2025, May 10). Agentic Artificial Intelligence in Public Administration: Foundations, Applications, and Governance. Applications, and Governance 2025. Available online: https://ssrn.com/abstract=5249100. source
- Partly supportedcites [42] 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. sourceExperimental — accuracy not yet measured
Our copy does present a coupled, closed-loop architecture: 'A. System Architecture of Agentic AI' states the system is 'composed of LAMs, knowledge bases, planners, tools, and memory modules' with the agent using memory 'to store and retrieve historical information for reflection and continuous task optimization'; '1) LAMs' adds multimodal perception/interpretation of external commands and environments plus reflective evaluation; '4) Tools' describes the execution bridge enabling 'perception-reasoning-action'; '5) Memory' and the MER module ('C. Multi-Agent System Architecture') describe evaluation/reflection feeding optimised plans 'back to the MCP module'. So perception, planning/reasoning, execution/tooling, evaluation/feedback and memory→planning are all supported. What is not supported is a distinct 'world/state modelling' layer: the paper's corresponding component is a knowledge base (external domain-knowledge retrieval and semantic reconstruction, cf. the MDR module), not world/state modelling, and the paper frames the loop as its LAM-based/CommLLM architecture ('input-reasoning-feedback-optimization', Fig. 4/Fig. 5) rather than as a general 'common integration pattern' across agentic systems. (LLM, conf=0.72)
- Partly supportedcites [95] Garg, 2025, Designing the Mind: How Agentic Frameworks Are Shaping the Future of AI Behavior, J. Comput. Sci. Technol. Stud. sourceExperimental — accuracy not yet measured
The Foundational Architecture of Agentic Systems section describes coordinated perception, world modeling, planning, and execution components. It also says execution monitoring can trigger replanning. It does not describe the claimed ordered loop with evaluation/feedback and memory as distinct stages, or establish that this full sequence is a common integration pattern; page numbers were not provided in our copy. (LLM, conf=0.85)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“layered neuro-symbolic approaches integrate neural inference with symbolic reasoning to manage uncertainty and provide traceability”
What the sources say
- Could not verifycites [39] Okpala, I., Golgoon, A., and Kannan, A.R. (2025). Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews. arXiv. sourceExperimental — accuracy not yet measured
Our copy of Okpala et al. (2025) never addresses neuro-symbolic methods: searches for 'neuro-symbolic', 'symbolic reasoning', 'knowledge graph', 'traceability' and 'managing uncertainty' returned only semantic neighbours — layered MEMORY (TradingGPT's long/middle/short-term layers, Intro p. 2), planning-module techniques like ReAct/Reflexion/Chain-of-Thought/Graph-of-Thought (§2, p. 6), guardrails and human-in-the-loop for transparency/traceability concerns (Intro pp. 4-5, §3.1 p. 8), and Future Directions (§4, p. 22). The nearest content is about layered memory hierarchies and LLM opacity mitigated by human oversight and logging, not about integrating neural inference with symbolic reasoning; the paper does not state the claim, nor anything contrary to it. (LLM, conf=0.72)
- Not checked — no full text of the sourcecites [41] Salah, M., Alnoor, A., Abdelfattah, F., and Al Halbusi, H. (2025, May 10). Agentic Artificial Intelligence in Public Administration: Foundations, Applications, and Governance. Applications, and Governance 2025. Available online: https://ssrn.com/abstract=5249100. source
- Partly supportedcites [95] Garg, 2025, Designing the Mind: How Agentic Frameworks Are Shaping the Future of AI Behavior, J. Comput. Sci. Technol. Stud. sourceExperimental — accuracy not yet measured
The Path Forward: Research Directions and Design Principles says neuro-symbolic architectures combine neural pattern recognition with symbolic reasoning. Challenges in Agentic AI Development discusses uncertainty handling and symbolic components that generate human-readable justifications, but does not establish that layered neuro-symbolic approaches themselves provide traceability or manage uncertainty. (LLM, conf=0.82)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“though at the cost of added integration complexity [39,41,95]”
What the sources say
- Could not verifycites [39] Okpala, I., Golgoon, A., and Kannan, A.R. (2025). Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews. arXiv. sourceExperimental — accuracy not yet measured
Our copy of Okpala et al. (2025) discusses layered/hierarchical designs — TradingGPT's long/middle/short-term memory layers (Introduction, p. 2) and horizontal/hierarchical/nested collaboration structures (§2, p. 7) — but presents them as capability gains, not as an integration burden, and never uses the term 'neuro-symbolic' or any symbolic-neural hybrid. The nearest cost statements are generic multi-agent challenges credited to [14] ('managing complex context information, and improving memory management', Introduction, p. 4) and a dual-agent compliance system that 'improves accuracy (up to 100%) but increases computational costs' (Introduction, p. 4) — computational cost, not integration complexity of layered neuro-symbolic approaches. Searched: neuro-symbolic, symbolic-neural hybrid, integration complexity, layered architecture overhead, trade-off/computational cost — no passage states the claim. (LLM, conf=0.65)
- Not checked — no full text of the sourcecites [41] Salah, M., Alnoor, A., Abdelfattah, F., and Al Halbusi, H. (2025, May 10). Agentic Artificial Intelligence in Public Administration: Foundations, Applications, and Governance. Applications, and Governance 2025. Available online: https://ssrn.com/abstract=5249100. source
- Supportedcites [95] Garg, 2025, Designing the Mind: How Agentic Frameworks Are Shaping the Future of AI Behavior, J. Comput. Sci. Technol. Stud. source
The “Challenges in Agentic AI Development” passage says integration challenges are particularly significant when neural components operate alongside symbolic modules. “Foundational Architecture of Agentic Systems” describes mediation layers needed to connect their different representations. Together, these support the claim of added integration complexity; page numbers were not provided. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
80 more claims · 13 with their cited sources checked
Create a free account to see all 299 claims and to verify the 112 references still open.
- It may state two separate claims as one. 137
- Probably not a substantial claim. 131
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?
The cited source doesn’t support the claim as written.
In the citing paper
“Although recent reviews have examined the capabilities, architectures, and clinical applications of agentic AI in healthcare, explainability has been largely treated as a conceptual requirement rather than an operational property of these systems [1,4,12].”
From Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review (2026) · cites this paper as [4]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Rather than having one LLM plan, execute, and evaluate tasks, the systems now orchestrate a series of specialized agents sharing context, critiquing one another, and modularizing the incident-response pipeline [30], [31], [32].”
From The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines (2026) · cites this paper as [32]
Experimental — accuracy not yet measuredIn the citing paper
“Prior studies have predominantly focused on China, Europe, and Western contexts, with limited empirical evidence from Middle Eastern higher education systems (Dahri et al., 2025; Dahri et al., 2025; Bandi et al., 2025).”
From Exploring the role of agentic AI in fostering self-efficacy, autonomy support, and self-learning motivation in higher education (2026) · cites this paper as Bandi et al., 2025
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2. Methodology
“More than 90% of these papers were published in 2024 and 2025”
§ Appendix A
“| 2024 | 21 | | 2025 | 93 | | Total | 143 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2. Methodology
“these 143 primary studies to extract the data, which were published from the year 2005 to the present”
§ Appendix A
“| 1999 | 1 |”
Citations
Cites
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941
A Survey on Large Language Model based Autonomous Agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.11432 · Cited by 1,925
Nguyen, T. T., Nguyen, N. D., & Nahavandi, S. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2977374 · Cited by 1,306
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
Zhang, K., Yang, Z., & Başar, T. (2021) · Studies in Systems, Decision and Control · doi:10.1007/978-3-030-60990-0_12 · Cited by 1,264
MASON: A Multiagent Simulation Environment
Luke, S., Cioffi-Revilla, C., Panait, L., Sullivan, K., & Balan, G. (2005) · SIMULATION · doi:10.1177/0037549705058073 · Cited by 1,000
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
A survey and critique of multiagent deep reinforcement learning
Hernandez-Leal, P., Kartal, B., & Taylor, M. E. (2019) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-019-09421-1 · Cited by 671
A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024) · Vicinagearth · doi:10.1007/s44336-024-00009-2 · Cited by 404
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
Li, G., Hammoud, H. A. A. K., Itani, H., Khizbullin, D., & Ghanem, B. (2023) · arXiv · doi:10.48550/arxiv.2303.17760 · Cited by 315
Camel: Communicative agents for" mind" exploration of large language model society
Li, G., Hammoud, H., Itani, H., Khizbullin, D., & Ghanem, B. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2264 · Cited by 314
Research works printed but not linked: 28
- Jin, H., Huang, L., Cai, H., Yan, J., Li, B., and Chen, H. (2024). From llms to llm-based agents for software engineering: A survey of current, challenges and future. arXiv.
- Sami, A.M., Rasheed, Z., Kemell, K.K., Waseem, M., Kilamo, T., Saari, M., Duc, A.N., Systä, K., and Abrahamsson, P. (2024). System for systematic literature review using multiple ai agents: Concept and an empirical evaluation. arXiv.
- Schneider, J. (2025). Generative to agentic ai: Survey, conceptualization, and challenges. arXiv.
- Pavani, S., and Shwetha, H. (2025, August 14). Agentic AI: Redefining Autonomy for Complex Goal-Driven Systems. Available online: https://scholar.google.com/scholar?hl=en&as_sdt=0%2C26&q=Agentic+AI%3A+Redefining+Autonomy+for+Complex+Goal-Driven+Systems.&btnG=.
- Botti, V. (2025). Agentic AI and Multiagentic: Are We Reinventing the Wheel?. arXiv.
- Huang, L., Koutra, D., Kulkarni, A., Prioleau, T., Wu, Q., Yan, Y., Yang, Y., Zou, J., and Zhou, D. (May, January 28). Towards Agentic AI for Science: Hypothesis Generation, Comprehension, Quantification, and Validation. Proceedings of the Companion Proceedings of the ACM on Web Conference, Sydney, Australia.
- Wissuchek, C., and Zschech, P. (2025). Exploring Agentic Artificial Intelligence Systems: Towards a Typological Framework. arXiv.
- Raidas, M.A., and Bhandari, R. (2025). Agentic AI in Education: Redefining Learning for the Digital Era. Artificial Intelligence in EducationTransforming Learning for the Future, Scholars’ Press.
- (2025, January 19–23). Multimodal Agentic Model Predictive Control. Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, Detroit, MI, USA.
- Paleti, 2024, Agentic AI in Financial Decision-Making: Enhancing Customer Risk Profiling, Predictive Loan Approvals, and Automated Treasury Management in Modern Banking, Multidiscip. Sci. Work. Manag. J., 34, 832
- Trirat, P., Jeong, W., and Hwang, S.J. (2025). Agentic Predictor: Performance Prediction for Agentic Workflows via Multi-View Encoding. arXiv.
- Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S.K.S., and Lin, Z. (2024, January 7–11). MetaGPT: Meta programming for a multi-agent collaborative framework. Proceedings of the International Conference on Learning Representations, ICLR, Vienna, Austria.
- Liu, Z., Yao, W., Zhang, J., Yang, L., Liu, Z., Tan, J., Choubey, P.K., Lan, T., Wu, J., and Wang, H. (2024). AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System. arXiv, 15538.
- Thirumalainambi, R. (2007, January 9–12). Pitfalls of JESS for Dynamic Systems. Proceedings of the Artificial Intelligence and Pattern Recognition, Citeseer, Orlando, FL, USA.
- Silver, T., Hariprasad, V., Shuttleworth, R.S., Kumar, N., Lozano-Pérez, T., and Kaelbling, L.P. (2025, August 14). PDDL planning with pretrained large language models. In Proceedings of the NeurIPS 2022 Foundation Models for Decision Making Workshop. Available online: https://drive.google.com/file/d/1PqCYzzfdUFitxG7NxFs0D6dn-TzI97q_/view.
- (2025, January 16–19). Nurturing Code Quality: Leveraging Static Analysis and Large Language Models for Software Quality in Education. In Proceedings of the Adjunct 33rd ACM Conference on User Modeling, Adaptation and Personalization. New York, NY, USA.
- Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., and Cao, Y. (2023, January 1–5). ReAct: Synergizing Reasoning and Acting in Language Models. Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda.
- Kim, J., Wahi-Anwa, M., Park, S., Shin, S., Hoffman, J.M., and Brown, M.S. (2025). Autonomous Computer Vision Development with Agentic AI. arXiv.
- Jeyakumar, S.K., Ahmad, A.A., and Gabriel, A.G. (2024, January 16). Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset. Proceedings of the NeurIPS 2024 Workshop on Open-World Agents, Vancouver, BC, Canada.
- Casper, S., Bailey, L., Hunter, R., Ezell, C., Cabalé, E., Gerovitch, M., Slocum, S., Wei, K., Jurkovic, N., and Khan, A. (2025). The AI Agent Index. arXiv.
- Sheriff, A., Huang, K., Nemeth, Z., and Nakhjiri, M. (2025). ADA: Automated Moving Target Defense for AI Workloads via Ephemeral Infrastructure-Native Rotation in Kubernetes. arXiv.
- Bennett, J., and Sterritt, R. (2024, January 10–14). Autonomic Computing in Total Achievement of Quality. Proceedings of the The Twentieth International Conference on Autonomic and Autonomous Systems, Athens, Greece.
- Inala, 2025, Building Trustworthy Agentic Ai Systems FOR Personalized Banking Experiences, Metall. Mater. Eng., 31, 1336
- Huang, C., Huang, H., Yu, T., Xie, K., Wu, J., Zhang, S., Mcauley, J., Jannach, D., and Yao, L. (2025). A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms. arXiv.
- Zhang, Q., Wornow, M., and Olukotun, K. (2025). Cost-Efficient Serving of LLM Agents via Test-Time Plan Caching. arXiv.
- (2025, August 14). AI Agents: Potential implications for IS Research?. Available online: https://www.sciencedirect.com/science/article/pii/S0963868725000216.
- Zhou, R., Sikand, V., and Rao, S. (2025, January 27). AI Agents for Deep Scientific Research. Proceedings of the UIUC Spring 2025 CS598 LLM Agent Workshop, Urbana, Illinois, USA. Available online: https://openreview.net/forum?id=wODNrFtTT2.
- Mukherjee, A., and Chang, H.H. (2025). Agentic AI: Expanding the Algorithmic Frontier of Creative Problem Solving. arXiv.
Cited by
Alqurni, J. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1738774 · Cited by 58
“Prior studies have predominantly focused on China, Europe, and Western contexts, with limited empirical evidence from Middle Eastern higher education systems (Dahri et al., 2025; Dahri et al., 2025; Bandi et al., 2025).”
The role of agentic artificial intelligence in healthcare: a scoping review
Collaço, B. G., Haider, S. A., Prabha, S., Gomez-Cabello, C. A., Genovese, A., Wood, N. G., Bagaria, S. P., Gopala, N., Tao, C., & Forte, A. J. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02517-5 · Cited by 130
“…as a personal medical assistant during trauma resuscitation, was a prototype that employed two cooperating agents based on the Belief-Desire-Intention (BDI) model, a classic reasoning architecture in which beliefs represent knowledge, desirescapture goals, and intentions de fi ne actions 10 .”
InfluentialThe Rise of Agentic AI: Synthesis of Current Knowledge and Future Research Agenda
Islam, M. A., Somu, S., & Aldaihani, F. M. F. (2025) · Global Business and Organizational Excellence · doi:10.1002/joe.70019 · Cited by 59
Hybrid agentic AI and multi-agent systems in smart manufacturing
Farahani, M. A., Khan, M. I., & Wuest, T. (2026) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2026.04.002 · Cited by 53
“Recent advances in foundation language models [15] have given rise to Agentic AI which is defined as autonomous, goal-directed AI systems with reasoning , planning , memory , and tool-use capabilities [16].”
Agentic AI for smart manufacturing
Lee, J., & Su, H. (2025) · Manufacturing Letters · doi:10.1016/j.mfglet.2025.10.013 · Cited by 42
Goyez, J. P. L., González‐Briones, A., & Demazeau, Y. (2026) · Applied Sciences · doi:10.3390/app16031323 · Cited by 33
Ethical perspectives on AI Agents and Agentic AI
Hahn, M., Tretter, M., & Dabrock, P. (2026) · AI and Ethics · doi:10.1007/s43681-026-01027-0 · Cited by 17
AgentBound: 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
Márquez, A. C., & Fernández, J. F. G. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131767 · Cited by 15
Evaluating and regulating agentic AI: A study of benchmarks, metrics, and regulation
Farooq, A., Raza, S., Karim, N., Iqbal, H., Vasilakos, A. V., & Emmanouilidis, C. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104444 · Cited by 25
Telemetry and Agentic AI: Foundations for Optical Network Automation
Cruzes, S. (2025) · IEEE Access · doi:10.1109/access.2025.3649768 · Cited by 17
“A recent survey on agentic systems highlights a key insight that directly reinforces the framework view described in this manuscript [16].”
InfluentialA Critical Review and Evaluation of LLMs for RTL Generation
Ravindran, A., Patra, A., Babaey, V., & Purini, S. (2026) · IEEE Access · doi:10.1109/access.2026.3665894 · Cited by 10
“We analyze this evolving body of work to identify the techniques explored—ranging from prompt engineering [8], retrieval augmented generation [9], multi-agent LLM systems [10], [11], fine-tuning [12], tool use [13] and reinforcement learning [14]—and to chart how the field has progressed.”
Jôrgensen, B. N., & Ma, Z. G. (2026) · Energies · doi:10.3390/en19061472 · Cited by 7
AI Agent Communications in the Future Internet—Paving a Path Toward the Agentic Web
Duan, Q., & Lu, Z. (2026) · Future Internet · doi:10.3390/fi18030171 · Cited by 12
Systematic Review: Agentic AI in Neuroradiology: Technical Promise with Limited Clinical Evidence
Salehi, S., Keishing, V., Singh, Y., Wei, D., Khosravi, A., Habibi, P., Jagtap, J. M. M., & Erickson, B. J. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-025-01839-2 · Cited by 5
Vinay, V. (2026) · 2026 IEEE 5th International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395809 · Cited by 15
“Rather than having one LLM plan, execute, and evaluate tasks, the systems now orchestrate a series of specialized agents sharing context, critiquing one another, and modularizing the incident-response pipeline [30], [31], [32].”
Graph Combinatorial Optimization Problems for Blockchain Transaction Network Analysis
Palk, M., & Voß, S. (2026) · Mathematics · doi:10.3390/math14020345 · Cited by 6
Roumeliotis, K. I., Margaris, D., Spiliotopoulos, D., & Vassilakis, C. (2026) · Future Internet · doi:10.3390/fi18020112 · Cited by 4
Jiang, Z., Xu, W., & Dong, B. (2026) · Advances in Applied Energy · doi:10.1016/j.adapen.2026.100273 · Cited by 9
From benchmarks to deployment: a comprehensive review of agentic AI evaluation
Kehkashan, T., Abdullah, M. I., Al‐Shamayleh, A. S., Ivković, N., Ismail, N. A., Ahmad, S. S. S., Rehman, A., & Akhunzada, A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11571-0 · Cited by 19
One Yeast, Sixteen Synthetic Chromosomes, Infinite Possibilities
Archer, E., Walker, R. S. K., Erpf, P. E., Paulsen, I. T., & Pretorius, I. S. (2026) · Yeast · doi:10.1002/yea.70026 · Cited by 5
“Agentic AI systems, capable of goal definition and iterative learning, offer a natural extension to DBTL pi-pelines on the genome scale (Bandi et al. 2025; Wang et al. 2025b).”
Anchala, S. (2026) · Journal of Integrative Science and Societal Impact · doi:10.29121/jissi.v2.i1.2026.37 · Cited by 2
Lazaropoulos, A. G. (2026) · Sustainability · doi:10.3390/su18073369 · Cited by 2
Trad, F. S., & Chehab, A. (2026) · Information Processing & Management · doi:10.1016/j.ipm.2026.104834 · Cited by 3
FinNutriAgent (FNA): An Agentic AI for Nutrition Planning Considering Budget Constraints
Syed, T. A., Alshahrani, A., Akarma, A., Khan, S., Nauman, M., Lee, I. E., Jan, S., & Ullah, A. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.15640 · Cited by 6
“Nevertheless, the majority of current consumer-facing solutions focus on convenience and operational efficiency; consequently, health and financial outcomes remain under-researched [15].”
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
Autonomy is not enough: why agentic AI in the built environment demands governance
Tam, N. V. (2026) · Energy and Buildings · doi:10.1016/j.enbuild.2026.117865 · Cited by 2
The digital therapist? LLMs and the future of clinical dialogue
Shi, E. R., Pei, R., & Barceló-Coblijn, L. (2026) · Language and Health · doi:10.1016/j.laheal.2026.100086 · Cited by 5
Kumar, G. (2025) · doi:10.38124/ijisrt/25sep616 · Cited by 1
“As an illustration, the biased portfolio suggestions can lead to the unfair treatment of customers of the disadvantaged groups (Bandi et al., 2025).”
InfluentialSuyunovna, K. D., Niyazova, N., Salayeva, L., Ahmad, M., & Sharifzoda, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4621-2.ch008 · Cited by 1
Panda, S., & Padhy, A. (2025) · International Conference on Mobile Networks and Wireless Communications (ICMNWC) · doi:10.1109/icmnwc66779.2025.11354453 · Cited by 2
“Multi-agent reinforcement learning (MARL) addresses situations where multiple agents explore to optimize returns, either cooperatively or competitively [6].”
The nature of agency: designing agentic systems using a biomimetic lens
Malik, T., Hughes, L., Dwivedi, Y. K., Mello, N. D., Barahona, I., & Jeon, I. (2026) · Journal of Systems and Information Technology · doi:10.1108/jsit-07-2025-0306 · Cited by 2
A Systematic Literature Review on Agentic AI Insights in Hospitality Industry
Arunkumar, S. (2025) · International Journal of Research & Technology · doi:10.64882/ijrt.v13.is4.798 · Cited by 1
“…in modern organizations is Agentic AI (Hosseini & Seilani, 2025; Pati, 2025), which is a multi-agent system that does more than simply respond to commands; it can also choose tools, set subgoals, and carry out multistep actions to accomplish user goals with limited supervision (Bandi et al., 2025).”
Ayouni, S., Khan, R. A., Maddeh, M., Alwageed, H. S., Keshta, I. M., & Almagrabi, A. O. (2026) · Egyptian Informatics Journal · doi:10.1016/j.eij.2026.100915 · Cited by 6
Secure Agent-Based Architectures for Decentralized AI Identity Management: The DAIS Framework
Ragupathy, V. (2026) · IEEE International Conference on AI in Cybersecurity (ICAIC) · doi:10.1109/icaic67076.2026.11395719 · Cited by 1
“Show industry adoption of decentralised identification in banking, healthcare, supply chain, and business governance production [17].”
Nanda, S. K., Tripathy, D. P., & Ray, N. K. (2025) · OITS International Conference on Information Technology (OCIT) · doi:10.1109/ocit66168.2025.11400090 · Cited by 1
“After approval, the project’s environmental performance is tracked through continuous monitoring and evaluation to ensure compliance [6].”
Immersive Training for the AI-Enabled Factory
Azeroual, O. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5756-0.ch002 · Cited by 2
FinAgent: An Agentic AI Framework Integrating Personal Finance and Nutrition Planning
Syed, T. A., Jan, S., Alshahrani, A. M., Khan, S., & Akarma, A. (2025) · International Conference on Computer and Applications (ICCA) · doi:10.1109/icca66035.2025.11430760 · Cited by 11
“It drives the retail, travel, and shopping agents that operate round the clock, but most of them are aimed at convenience, not health or financial welfare [15].”
Mahlaole, S. T., & Malebana, M. J. (2026) · Future Business Journal · doi:10.1186/s43093-026-00788-8 · Cited by 2
May, P., Brookman-May, S. D., Garrahy, E., & von Büren, J. (2026) · Journal of Medical Internet Research · doi:10.2196/92642 · Cited by 2
“Recent reviews describe the rapid proliferation of these tools in oncology yet consistently highlight that their translation into practice is constrained not by algorithmic performance but by integration challenges, data quality, and safety governance [7-13].”
Persuading the proxy: a framework for AI-mediated marketing decisions
Bilgihan, A., Lorenz, M. P., Zhang, Y., & Ostinelli, M. (2026) · International Journal of Contemporary Hospitality Management · doi:10.1108/ijchm-11-2025-1700 · Cited by 4
From Recommender to Actor: The Normative Boundary When RAG Tools Become Tool-Calling Agents
Rashid, M. T. (2026) · Minds and Machines · doi:10.1007/s11023-026-09782-z · Cited by 6
“As Bandi et al., (2025) notes, agentic systems increasingly display coordinated behavior across perception, reasoning, memory, and actuation.”
Islam, M. A., Almashayekhi, A. O., Rahman, M., & Somu, S. (2026) · VINE Journal of Information and Knowledge Management Systems · doi:10.1108/vjikms-01-2026-0004 · Cited by 3
Hasan, M. A., Kashef, A., Mohsen, W. A., Khan, A. G. Y., AlOmari, M., & Aishan, H. (2026) · Frontiers in Education · doi:10.3389/feduc.2026.1895511 · Cited by 1
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
“Benchmark environments that are realistic enough for ecologically valid evaluation yet controlled enough for reproducible comparison should cover diverse agentic settings [22], [48] and incorporate human-centered metrics alongside technical fidelity measures [35], [54].”
InfluentialAgentic AI: From Autonomous Agents to Enterprise Agentic AI Systems
Li, M. M., Reinhard, P., & Leimeister, J. M. (2026) · Business & Information Systems Engineering · doi:10.1007/s12599-026-01009-w · Cited by 9
“Third , we connect to recent work on AI agents and agentic AI (e.g., Acharya et al. 2025; Sapkota et al. 2025; Bandi et al. 2025), from which we synthesize emerging agentic capabilities.”
AI Agents and the Progressive Intermediation Between Users and Online Services: A Critical Analysis
Rondina, M., Vetrò, A., Martin, J. C. D., Bargis, M., & Elia, G. (2026) · Future Internet · doi:10.3390/fi18080419 · Cited by 1
“There is growing scholarly attention to AI agents, such as technical contributions focusing on architectures, applications, and limitations [7–9].”
Sorooshian, S., Ahadi, N., & Liravi, P. (2026) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2026.101631 · Cited by 4
-, S. B., Ranjan, S., Adhitya, M., Suri, V., Hassija, V., Chamola, V., & Hussain, A. (2026) · Cognitive Computation · doi:10.1007/s12559-026-10619-1 · Cited by 10
“This harmonized vocabulary will be used consistently in the rest of the paper [46].”
DASH: Designing and Developing Agentic Systems for Humans (Tutorial)
Brachman, M., Candello, H. C. D. S. P., & da Silveira, A. S. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742414.3794949
Wang, Y., Lei, K., Chiu, S., Isbister, K., Lee, D. T., & Ringland, K. E. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791880 · Cited by 5
“SeeSawBot followed a sense-plan-act pipeline (see Figure 3 ), inspired by classical robotics architectures [10, 74] and conceptually related to recent LLM-based agentic systems that employ sequential perceive-plan-act structures [4, 21, 61, 62].”
IMMUNIA: A Multi-LLM Reasoning Agent for Immunoregulatory Surfaceome DiscoveryPreprint
Park, N., & Lee, J. H. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.11.02.686138
“The rise of agentic AI frameworks, which coordinate autonomous model interactions and critical evaluation loops, further enables systematic and reproducible knowledge discovery 28 .”
Pedagogical Transformations: Agentic AI as a Co-Teacher and Learning Partner
Taskarayevna, N. Z., Yuldibayevna, B. G., Niyazova, N., Shehzadi, I., & Turayev, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-4621-2.ch004 · Cited by 15
Márquez, A. C., & Fernandez, J. F. G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5985157
Self-Learning Agentic AI Cloud Platforms for Dynamic Enterprise Process Automation
Kaza, P. R., & Manduva, V. C. (2025) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom67567.2025.11331327
“From recent studies, governance and compliance comprise a top barrier in moving agentic AI from pilot to scale in enterprise environments [1], [2].”
Agentic AI for Conversational Flight Reservation Systems
Rishwanth, S., Yashwanth, L., & Shiny, R. M. (2025) · International Conference on Mobile Networks and Wireless Communications (ICMNWC) · doi:10.1109/icmnwc66779.2025.11354415 · Cited by 1
Agentic AI-Driven Decision Orchestration System for Real-Time Project Coordination
Harini, P., Thota, B., Shamim, et al. (2025) · International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF) · doi:10.1109/iceconf65644.2025.11379478
“…networked economy requires a very special type of complexity in projects, since a globally coordinated supply chain, the related labor forces and the digital framework, which consolidates it all, must also include a dynamic coordination of the team members and the associated automation [1].”
Agentic AI for Automated Grading: System Design, Baseline Study, and Empirical Evaluation
Saputra, D. M., Simarmata, R. H., Buchari, M. A., Faridi, M. A., Ramadhan, M. M. L., & Iqrom, R. A. (2025) · International Conference on Artificial Intelligence and Technological Solutions (ICAITech) · doi:10.1109/icaitech66481.2025.11387255
“Agentic AI or AI agent is a system that can reason, plan and take actions on its own based on information its given [11,14,22].”
May, P., Brookman-May, S., Garrahy, E., & von Büren, J. (2026) · doi:10.2196/preprints.92642
Yadav, S., Sam, A. K., Jitto, J., & Jai Vinita, L. (2026) · International Conference on Computational Intelligence in Data Science (ICCIDS) · doi:10.1109/iccids69108.2026.11407690
“They often demonstrate a Lack of Emotional Depth, with poor dynamic empathy that fails to meet the user’s need for genuine emotional understanding [1], [3].”
Jiang, Z., Xu, W., & Dong, B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6353019
Toward a unified agentic framework for regime-aware portfolio optimization with LLM signals
Mantshimuli, L. A., & Mwamba, J. W. M. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01066-0
Uh, K. (2026) · The Korean Society of Costume · doi:10.7233/jksc.2026.76.1.071
Autonomous Service Delivery Systems with Agentic AI: A Conceptual Exploration
Tan, A. H. T., Choy, M., & Leo, K. C. (2026) · Springer eBooks · doi:10.1007/978-3-031-75316-9_103-1
From Prompt to Pipeline: Why and How AI-Assisted Workflows Harden into Deterministic SystemsPreprint
Ilagan, J. B., Uy, G. A., & Ilagan, J. R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6358278
An agentic AI marketplace for prelitigation analyses with ZKP-integrated ethical verifications
Udokwu, C. J., Dwivedi, V. K., Buick, A., Keers, J., & Liu, J. (2026) · Frontiers in Blockchain · doi:10.3389/fbloc.2026.1770848
A Critical Perspective on Adopting Generative AI in Marketing for Business Organizations
Zalan, T., & Toufaily, É. (2026) · Springer eBooks · doi:10.1007/978-3-031-75316-9_46-1
Agentic Automation Experiences—Rethinking the Interaction of Humans and AI Agents
Spitzer, P., Baldauf, M., Palanque, P. A., Roto, V., Morrison, K., Gomez-Beldarrain, G., Westphal, M., & Holstein, J. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3778732 · Cited by 1
Berger, M., Kujat, C., Guzmán-Merino, M., Krause, N. S., Grauer, D. G. D., & Ploennigs, J. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6572620
Vergara, D., & Fernández-Arias, P. (2026) · Future Internet · doi:10.3390/fi18040219
Gharib, M., Alsatouf, M., Alshanfari, M., Trivedi, A., & Trivedi, V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-15806-2_45
The Next Stage of Evolutionary Computation in the Era of Agentic Generative AI
Palk, M., Voß, S., & Glover, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-23607-4_19 · Cited by 1
Explainable Agentic Artificial Intelligence in Healthcare: A Scoping Review
Collaco, B. G., Prabha, S., Gomez-Cabello, C. A., Haider, S. A., Genovese, A., Wood, N. G., Gopala, N., Raman, R., Hester, E. O., & Forte, A. J. (2026) · Bioengineering · doi:10.3390/bioengineering13050513 · Cited by 3
“As such, agentic AI represents a potentially transformative paradigm for healthcare innovation, offering flexibility, scalability, and contextual reasoning capabilities that extend beyond traditional machine learning approaches [1,4].”
TRANSFORMATION OF THE DIGITAL TOURISM SYSTEM: FROM INTELLIGENT AGENTS TO AGENTIC AI
Mykhailichenko, H., Lysiana, V., & Schuka, H. (2026) · Baltic Journal of Economic Studies · doi:10.30525/2256-0742/2026-12-2-324-332 · Cited by 1
“The level of orchestration ensures that they are all aligned with the goal (Bandi et al., 2025).”
InfluentialMahmud, M. A., Rahman, M. M., Gomes, D., Tanvir, K., & Islam, M. R. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7355-3.ch010
Kaza, P. R. (2026) · IEEE International Conference on Emerging Computing and Intelligent Technologies (ICoECIT) · doi:10.1109/icoecit68303.2026.11497409
Karthick Sriram, M., Divya, P., P, G. V. K., & Mallika, S. (2026) · International Conference on Machine Learning and Autonomous Systems (ICMLAS) · doi:10.1109/icmlas67792.2026.11484017
“Improvements in agentic AI, big language models, and cognitive architectures have made it possible for systems to understand high-level goals, break them down into actions that can be carried out, and change based on feedback [5, 6, 7].”
Goal-Driven Agentic Intelligence for the Evolution of Energy Efficient Smart Cities
Yordanova, Z. B., Nozari, H., Hristozov, Y., & Kolyandov, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-1669-5.ch003
The Vanishing User: Web Analytics in an Agent-Dominated Internet
George, B., & Choudhary, D. (2026) · Information · doi:10.3390/info17050453 · Cited by 1
Agentic AI and the Algorithm of Good
Gounaris, A., & Kosteletos, G. (2026) · AI · doi:10.3390/ai7090352
“Among the most frequently discussed regulatory challenges are the prevention of algorithmic bias and the promotion of fairness and justice [50,54,204–207,212]; labour market Other major concerns include the requirement for meaningful and effective human over-sight and control…”
Influentialde Carvalho, L. M., Peças, P., & Jorge, D. P. (2026) · Sustainability · doi:10.3390/su18104787 · Cited by 1
Dai, L., Fan, C., & Lü, L. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01364-3
“The core of virtual simulation training process scoring is how to accurately describe learners’ behavior patterns from discrete and time-related operation logs, and on this basis, combine training norms and logical constraints to output consistent and interpre-table scoring results [21, 22].”
From Classical AI to Agentic Intelligence
de Oliveira, P., Pereira, J. D. C., & Nováis, P. (2026) · SpringerBriefs in intelligent systems · doi:10.1007/978-3-032-24781-0_1
Apostolou, S. A., Bosch, J., & Olsson, H. H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36587-3_22 · Cited by 1
Practical Application of the Case Study
Oliveira, P., Pereira, J. D. C., & Nováis, P. (2026) · SpringerBriefs in intelligent systems · doi:10.1007/978-3-032-24781-0_6
Agentic AI–Driven Autonomous Traffic Orchestration System for Sustainable Urban Mobility
Delsi Robinsha, S., Vanusha, D., Nas, V., & Anbarasi, A. (2026) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate69073.2026.11518814
“The controller is constant and thus it is unable to respond to any real time variations in the traffic flow and thus it can offer a reasonable point on which the effectiveness of adaptive and intelligent control measures can be measured objectively[10].”
Emerging Trends and Innovations in Agentic AI on Procurement
Nicoletti, B. (2026) · Springer eBooks · doi:10.1007/978-3-032-23024-9_19
Challenges in Supporting Agentic AI in Procurement
Nicoletti, B. (2026) · Springer eBooks · doi:10.1007/978-3-032-23024-9_15
Agentic Artificial Intelligence in Dentistry: A Practice-Focused Perspective for the Dental Team
Farooqi, O. A., DeNucci, D. J., & Moharrami, M. (2026) · European Journal of General Dentistry · doi:10.1055/s-0046-1822820
The Evolution of Software Testing - Industry Trends in Generative and Agentic AI
Verma, P., Joshi, V., & Verma, Y. (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11526717
“Inaccurate or hallucinating results through AI have been discovered as one of the greatest challenges [14].”
Agentic AI for Context-Aware and Autonomous Data Quality Assessment
Mubarak, F., & Fadlallah, H. (2026) · doi:10.1109/menacomm69507.2026.11532938
“Agentic AI refers to AI systems capable of autonomously pursuing goals, planning, and executing multi-step workflows with limited human intervention [9].”
Ayouni, S., Khan, R. A., Alwageed, H. S., Keshta, I. M., Almagrabi, A. O., & Alzahrani, M. (2026) · Egyptian Informatics Journal · doi:10.1016/j.eij.2026.100991
Between Civic AI and the Agentic State: The Pathways of Post-Digital Democratic Governance
Pane, S. (2026) · Journal of artificial intelligence for sustainable development. · doi:10.69828/4d4ktj
Chaoraingern, J., & Numsomran, A. (2026) · IEEE Access · doi:10.1109/access.2026.3699137 · Cited by 1
“No existing framework explicitly addresses the structural incompatibility between stateless LLM pipelines and the longitudinal demands of IPA and SROI assessment, leaving a fundamental architectural gap unaddressed [2], [3].”
InfluentialThe Impact of Multi-Agent Reorganization on Efficiency
Silem, A. E. H., Tamrabet, Z., Khanfar, R., et al. (2026) · Information · doi:10.3390/info17060557
Agentenbasierte Fahrgastinformationssysteme für den ÖPNV
Palk, M., & Voß, S. (2026) · HMD Praxis der Wirtschaftsinformatik · doi:10.1365/s40702-026-01283-y
(2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105062
Agentic AI Frameworks: Orchestration Architectures and Autonomous LLM-Based Reasoning Systems
Yashwanth, L., Rishwanth, S., & Shiny, R. M. (2026) · International Conference on Integrated Intelligence and Communication Systems (ICIICS) · doi:10.1109/iciics67880.2026.11483602 · Cited by 1
Enhancing GraphRAG Using LLM Generated Ontology from Text
Chowdhury, R. R., Shiono, Y., Goto, T., Tsuchida, K., & Bandi, A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-29003-8_25
Self-citation
Metadata
- Authors
- Bandi, A., Kongari, B., Naguru, R., Pasnoor, S., & Vilipala, S. V.
- Affiliations
- Northwest Missouri State University (US)
- Independent Researcher, Omaha, NE 68022, USA
- Corresponding author
- Bandi, Ajay
- ORCID
- Bandi, Ajay
- Venue
- Future Internet
- Publisher
- MDPI AG
- Published
- 2025-09-04
- Volume
- 17
- Issue
- 9
- Pages
- 404
- ISSN
- 1999-5903 (ISSN-L)
- OpenAlex
- W4414023998
- Semantic Scholar
- d9f0d979178e8e42c88e831ba4a1e4eca17f3e83
- Cited by
- 207
- References
- 100
- Citations by year
- 2026: 191 · 2025: 16
- FWCI
- 82.37
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Future Internet (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Keywords
- agentic AI, autonomous agents, large language models, agent architecture, planning, memory, reflection, multi-agent systems, autonomic computing, generative AI, evaluation metrics, agent coordination
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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.