The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges
Расцвет агентного искусственного интеллекта: обзор определений, фреймворков, архитектур, приложений, метрик оценки и проблем
2025-09-04
SCID: 54.1/8bhngmf6
Discuss with AI
Agentic AIEvaluation metricsGoal-driven reasoningLLM-based agentsMulti-agent systems
Figures from the paper
Abstract (AI)
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.
Key Findings
1
A synthesis of 143 primary studies examines LLM-based and non-LLM agentic systems, focusing on planning, memory, reflection, and goal pursuit.
2
Agentic AI evaluation is organized into qualitative and quantitative metrics, alongside testing methods for assessing system performance and reliability.
3
The review characterizes agentic AI as distinct from traditional AI, generative AI, and autonomous systems through autonomy, adaptability, and goal-driven reasoning.
4
The review identifies technical, architectural, coordination, ethical, and security challenges that limit responsible deployment and future advancement.
5
The study classifies agentic AI architectures, input–output mechanisms, and application domains, supported by tabular summaries of real-world case studies.
Research Object
agentic AI systems
Research Subject
their definitions, frameworks, architectures, applications, evaluation metrics, and technical, architectural, coordination, ethical, and security challenges
Publication Details
Publication Date
2025-09-04
Journal
Publisher
ISSN
Cited by
207
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
A survey on large language model based autonomous agents2024
A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges2024
Artificial intelligence for literature reviews: opportunities and challenges2024
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges2025
AI Agents and Agentic Systems: A Multi-Expert Analysis2025
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations2025
AgentAI: A comprehensive survey on autonomous agents in distributed AI for industry 4.02025
Agentic AI Frameworks in SMMEs: A Systematic Literature Review of Ecosystemic Interconnected Agents2025
Cited by11
The role of agentic artificial intelligence in healthcare: a scoping review2026
Exploring the role of agentic AI in fostering self-efficacy, autonomy support, and self-learning motivation in higher education2026
Hybrid agentic AI and multi-agent systems in smart manufacturing2026
From benchmarks to deployment: a comprehensive review of agentic AI evaluation2026
Toward autonomous artificial intelligence agents in sports science: a modular framework for development, validation, and implementation2026
Ethical perspectives on AI Agents and Agentic AI2026
Evaluating and regulating agentic AI: A study of benchmarks, metrics, and regulation2026
Agentic AI: From Autonomous Agents to Enterprise Agentic AI Systems2026
Agentic AI Frameworks: Orchestration Architectures and Autonomous LLM-Based Reasoning Systems2026
AI Agents and Agentic AI in plant breeding: new frontiers, opportunities and challenges2026
The CO2ST of Agentic AI in Research2026