构建去中心化智能体网络，让AI自主组队完成任务
Internet of Agentic AI: Incentive-Compatible Distributed Teaming and Workflow
- 智能体在云边端动态组队，按需协作执行任务
- 提出激励相容机制，确保协作可实现且经济可行
- 适合需要弹性、抗故障的复杂AI系统设计者
大型语言模型（LLMs）催生了新型自主智能体系统，能够推理、规划并调用外部工具。然而，现有架构多为集中式与单体结构，限制了可扩展性、专业化和互操作性。本文提出可扩展智能体智能框架——‘智能体互联网’，使分布在云与边缘基础设施上的异构自主智能体能够动态组建联盟，执行以任务为导向的工作流。我们形式化了一种原生网络的智能体协作模型，并引入一个集成能力覆盖、网络局部性和经济可实施性的激励相容工作流联盟可行性框架。为实现可扩展协调，提出最小努力联盟选择问题及去中心化联盟形成算法。该框架可作为模型上下文协议（MCP）之上的协调层运行。医疗案例研究展示了领域专业化、云边异构性与动态联盟形成如何实现可扩展、有韧性和经济可行的智能体工作流。本工作为新兴的智能体互联网时代奠定了原则性协调与可扩展性的基础。
原文摘要 · Abstract (English)
Large language models (LLMs) have enabled a new class of agentic AI systems that reason, plan, and act by invoking external tools. However, most existing agentic architectures remain centralized and monolithic, limiting scalability, specialization, and interoperability. This paper proposes a framework for scalable agentic intelligence, termed the Internet of Agentic AI, in which autonomous, heterogeneous agents distributed across cloud and edge infrastructure dynamically form coalitions to execute task-driven workflows. We formalize a network-native model of agentic collaboration and introduce an incentive-compatible workflow-coalition feasibility framework that integrates capability coverage, network locality, and economic implementability. To enable scalable coordination, we formulate a minimum-effort coalition selection problem and propose a decentralized coalition formation algorithm. The proposed framework can operate as a coordination layer above the Model Context Protocol (MCP). A healthcare case study demonstrates how domain specialization, cloud-edge heterogeneity, and dynamic coalition formation enable scalable, resilient, and economically viable agentic workflows. This work lays the foundation for principled coordination and scalability in the emerging era of Internet of Agentic AI.
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。