Agentic AI Frameworks: Architectures, Protocols, and Design Challenges

TL;DR

This paper systematically reviews and compares leading Agentic AI frameworks, analyzing their architectures, communication protocols, and challenges to guide future research in autonomous AI systems.

Contribution

It provides a comprehensive taxonomy of Agentic AI architectures and protocols, identifying key limitations and proposing directions for scalability and robustness improvements.

Findings

Established a taxonomy for Agentic AI systems

Analyzed communication protocols like CNP, A2A, ANP, and Agora

Identified open challenges and future research directions

Abstract

The emergence of Large Language Models (LLMs) has ushered in a transformative paradigm in artificial intelligence, Agentic AI, where intelligent agents exhibit goal-directed autonomy, contextual reasoning, and dynamic multi-agent coordination. This paper provides a systematic review and comparative analysis of leading Agentic AI frameworks, including CrewAI, LangGraph, AutoGen, Semantic Kernel, Agno, Google ADK, and MetaGPT, evaluating their architectural principles, communication mechanisms, memory management, safety guardrails, and alignment with service-oriented computing paradigms. Furthermore, we identify key limitations, emerging trends, and open challenges in the field. To address the issue of agent communication, we conduct an in-depth analysis of protocols such as the Contract Net Protocol (CNP), Agent-to-Agent (A2A), Agent Network Protocol (ANP), and Agora. Our findings not only establish a foundational taxonomy for Agentic AI systems but also propose future research directions to enhance scalability, robustness, and interoperability. This work serves as a comprehensive reference for researchers and practitioners working to advance the next generation of autonomous AI systems.