这篇论文把9个主流的智能体通信协议拆成5个维度做分类，告诉你哪种协议适合什么场景，以及未来会怎么演进。如果你在做多智能体系统，想选协议或者设计协议，这篇很有参考价值。
该论文提出一个包含对手方、负载、交互状态、发现机制和模式灵活性5个维度的分类法，对9个活跃维护的开源协议进行迭代分析。研究发现所有智能体间协议均结合混合负载与会话状态持久化，多数协议支持多个预定义模式，两个协议在运行时协商模式，显示模式灵活性趋势。去中心化发现仍属罕见。短期看协议将趋同统一智能体间与智能体-上下文通信，长期则可能发展为分层协议栈。
A Technical Taxonomy of LLM Agent Communication Protocols
As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standalone agents, robust communication protocols are becoming essential infrastructure for distributed agent networks. Nonetheless, the fragmented protocol landscape presents a significant interoperability challenge. This study develops a technical taxonomy to classify and analyze LLM agent communication protocols. Following an established iterative method, we defined the taxonomy's purpose, meta-characteristic, and ending conditions, then performed five iterations, three empirical-to-conceptual and two conceptual-to-empirical, on nine actively maintained open-source protocols with demonstrable adoption. The taxonomy comprises five dimensions: counterparty, payload, interaction state, discovery mechanism, and schema flexibility. Classification reveals recurring architectural patterns: all sampled agent-to-agent protocols combine hybrid payloads with session-state persistence; most protocols support multiple predefined schemas, and two negotiate schemas at runtime, indicating a trend toward schema flexibility; decentralized discovery remains rare. Analysis suggests short-term convergence pressure toward protocols unifying agent-to-agent and agent-to-context (tool and data) communication. Long-term, however, no single protocol is likely to maximize versatility, efficiency, and portability simultaneously. The field will more likely evolve toward a federated, layered protocol stack. The framework guides protocol selection and highlights open research gaps such as privacy and policy enforcement.}