Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions

TL;DR

This survey introduces a dual-paradigm framework for agentic AI, categorizing systems into symbolic/classical and neural/generative, analyzing their architectures, applications, and ethical challenges across various domains.

Contribution

It presents a novel dual-paradigm framework for agentic AI, systematically reviews 90 studies, and offers a strategic roadmap for integrating symbolic and neural systems.

Findings

Symbolic systems dominate safety-critical domains like healthcare.

Neural systems are prevalent in adaptive, data-rich environments such as finance.

There is a significant gap in governance models for symbolic systems.

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but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual retrofitting.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.