构建可互操作的智能体协作系统，打破封闭生态困局
Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems
- 提出Web of Agents架构，包含四大基础组件
- 通过最小化标准实现跨生态兼容，避免碎片化
- 适合关注AI生态协同与系统集成的研究者
协作式智能体人工智能有望重塑整个行业，使智能体能在数字环境中自主感知、规划并行动。然而，当前解决方案均孤立构建，正迅速走向碎片化、不兼容的生态系统。本文主张，通过采用最小化标准实现互操作性，是确保开放、安全、可扩展且广泛采纳的智能体生态系统的必要条件。为此，我们设计了名为Web of Agents的最小化架构基础，由四个核心组件构成：智能体间通信、交互兼容性、状态管理与智能体发现。该架构复用现有标准与基础设施，为可互操作智能体系统迈出关键一步，提供在生态碎片化成为常态前的务实路径。
原文摘要 · Abstract (English)
Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we are rapidly heading toward a landscape of fragmented, incompatible ecosystems. In this position paper, we argue that interoperability, achieved by the adoption of minimal standards, is essential to ensure open, secure, web-scale, and widely-adopted agentic ecosystems. To this end, we devise a minimal architectural foundation for collaborative agentic AI, named Web of Agents, which is composed of four building blocks: agent-to-agent messaging, interaction interoperability, state management, and agent discovery. Web of Agents adopts existing standards and reuses existing infrastructure where possible. With Web of Agents, we take the first but critical step toward interoperable agentic systems and offer a pragmatic path forward before ecosystem fragmentation becomes the norm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。