如果你在选agent通信协议，这篇把MCP、A2A等9个协议的底层模式画清楚了，指出状态化会话是共识，去中心化发现还缺。
该报告构建了五维分类法（对手方、载荷、交互状态、发现机制、模式灵活性），分析了九个活跃维护的开源智能体协议，包括MCP和A2A。报告发现每个智能体间协议都采用混合载荷与会话状态持久化组合，而去中心化发现机制仍属罕见。该研究映射了当前LLM agent通信层的标准化趋势，为选择通信层提供依据。论文地址：arxiv.org/abs/2606.19135。
Great report on LLM agent communication protocols. Communication is a huge bottleneck in multi-agen...
Great report on LLM agent communication protocols. Communication is a huge bottleneck in multi-agent systems. (worth bookmarking) The report builds a five-dimensional taxonomy (counterparty, payload, interaction state, discovery mechanism, schema flexibility) across nine actively maintained open-source agent protocols, so it maps the real MCP and A2A landscape. Two patterns stand out. Every agent-to-agent protocol sampled pairs of hybrid payloads with session-state persistence, and decentralized discovery is still rare. So the field is quietly standardizing on stateful sessions while leaving discovery and policy enforcement open. Why does it matter? If you are choosing a communication layer this year, this discusses what nine real protocols actually do. Paper: arxiv.org/abs/2606.19135 Learn to build effective AI agents in our academy: academy.dair.ai 💬 0 🔄 3 ❤️ 18 👀 3060 📊 8 ⚡