A Survey of AI Agent Protocols

2025-04-23

AI Summary

Large language model (LLM) agents face fragmented communication protocols when orchestrating across heterogeneous tools and data sources, hindering scalability, security guarantees, and real-world task adaptability. To address this, we propose the first four-dimensional taxonomy—functional, semantic, interactive, and deployment-oriented—for systematically classifying and analyzing four mainstream protocol paradigms. We design a cross-protocol standardized evaluation framework, employing multidimensional benchmarking to expose fundamental trade-offs among security, latency, and scalability. Our analysis identifies critical bottlenecks in existing protocols and articulates adaptive protocol design principles and evolutionary pathways tailored to dynamic, open ecosystems. Key contributions include: (1) a reusable protocol selection decision matrix; (2) an architectural feasibility assessment report; and (3) a design guideline for next-generation protocol infrastructure—enabling principled, extensible, and secure LLM agent interoperability.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM agents are deployed, a major issue has emerged: there is no standard way for these agents to communicate with external tools or data sources. This lack of standardized protocols makes it difficult for agents to work together or scale effectively, and it limits their ability to tackle complex, real-world tasks. A unified communication protocol for LLM agents could change this. It would allow agents and tools to interact more smoothly, encourage collaboration, and triggering the formation of collective intelligence. In this paper, we provide a systematic overview of existing communication protocols for LLM agents. We classify them into four main categories and make an analysis to help users and developers select the most suitable protocols for specific applications. Additionally, we conduct a comparative performance analysis of these protocols across key dimensions such as security, scalability, and latency. Finally, we explore future challenges, such as how protocols can adapt and survive in fast-evolving environments, and what qualities future protocols might need to support the next generation of LLM agent ecosystems. We expect this work to serve as a practical reference for both researchers and engineers seeking to design, evaluate, or integrate robust communication infrastructures for intelligent agents.

Problem

• Lack of standardized protocols for LLM agent communication
• Difficulty in agent collaboration and scalability
• Need for unified protocols to enhance collective intelligence

Innovation

• Survey of LLM agent communication protocols
• Classify protocols into four categories
• Analyze performance on security, scalability, latency