Agentic AI: a comprehensive survey of architectures, applications, and future directions
Agentic AI: всесторонний обзор архитектур, приложений и направлений развития
2025-11-14
SCID: 54.1/ayfjt2kk
Discuss with AI
Agentic AIPRISMA-based reviewconceptual retrofittingdomain-specific implementations (healthcare, finance, robotics)dual-paradigm frameworkethical and governance challengeshybrid neuro-symbolic architecturesneural/generative paradigmsafety-critical domainssymbolic/classical paradigm
Figures from the paper
Abstract (AI)
Abstract Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models—a practice known as conceptual retrofitting . This survey cuts through this confusion by introducing a novel dual-paradigm framework that categorizes agentic systems into two distinct lineages: the symbolic/classical (relying on algorithmic planning and persistent state) and the neural/generative (leveraging stochastic generation and prompt-driven orchestration). Through a systematic PRISMA-based review of 90 studies (2018–2025), we provide a comprehensive analysis structured around this framework across three dimensions: (1) the theoretical foundations and architectural principles defining each paradigm; (2) domain-specific implementations in healthcare, finance, and robotics, demonstrating how application constraints dictate paradigm selection; and (3) paradigm-specific ethical and governance challenges, revealing divergent risks and mitigation strategies. Our analysis reveals that the choice of paradigm is strategic: symbolic systems dominate safety-critical domains (e.g., healthcare), while neural systems prevail in adaptive, data-rich environments (e.g., finance). Furthermore, we identify critical research gaps, including a significant deficit in governance models for symbolic systems and a pressing need for hybrid neuro-symbolic architectures. The findings culminate in a strategic roadmap arguing that the future of Agentic AI lies not in the dominance of one paradigm, but in their intentional integration to create systems that are both adaptable and reliable . This work provides the essential conceptual toolkit to guide future research, development, and policy toward robust and trustworthy hybrid intelligent systems.
Key Findings
1
Application constraints dictate paradigm selection, with domain-specific implementations examined in healthcare, finance, and robotics.
2
Concludes that future Agentic AI should intentionally integrate both paradigms rather than favor one dominant approach.
3
Highlights a pressing need for hybrid neuro-symbolic architectures to combine adaptability and reliability.
4
Identifies a significant deficit in governance models for symbolic systems and divergent ethical/governance challenges between paradigms.
5
Introduces a dual-paradigm framework categorizing agentic AI into symbolic/classical and neural/generative lineages.
6
Neural/generative systems prevail in adaptive, data-rich domains (e.g., finance) leveraging stochastic generation and prompt-driven orchestration.
7
Symbolic systems dominate safety-critical domains (e.g., healthcare) due to algorithmic planning and persistent state requirements.
8
Systematic PRISMA-based review of 90 studies (2018–2025) structures analysis across theory, applications, and ethics/governance.
Research Object
Agentic AI systems (symbolic/classical and neural/generative lineages)
Research Subject
Comparative architectures, domain implementations, ethical/governance challenges, and integration strategies (including need for hybrid neuro-symbolic architectures) of agentic AI across symbolic and neural paradigms
Publication Details
Publication Date
2025-11-14
Journal
Publisher
ISSN
Cited by
178
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai7
The PRISMA 2020 statement: an updated guideline for reporting systematic reviews2021
PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews2021
A Survey of Large Language Models2026
A survey on large language model based autonomous agents2024
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery2024
Visibility into AI Agents2024
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges2025
Cited by5
Evaluating routing stability and coordination in swarm-based multi-agent task-oriented dialogue systems2026
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security2026
Toward Sustainable Agentic AI Systems: A Survey of Architectures and Methodologies2026
Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems2026
A Hierarchical Failure Taxonomy for Reliability Assessment of AI Agents: An Empirical Analysis of the Agent Failure Atlas 2026 Benchmark2026