The Agent Operating System (AOS): A Reference Operating Architecture for Distributed Agentic Systems
作者: Ankur Sharma, Deep Shah
分类: cs.AI
发布日期: 2026-08-04
💡 一句话要点
提出Agent操作系统以解决分布式智能系统架构问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 分布式系统 智能代理 操作系统 治理架构 运行时协调 中立架构 系统集成
📋 核心要点
- 现有的智能系统架构缺乏稳定性和一致性,无法有效管理意图和授权。
- 本文提出Agent操作系统(AOS),作为一种中立的参考架构,包含控制与治理平面和运行时与协调平面。
- AOS的设计旨在整合异构组件,提升系统的治理能力和可靠性,确保可观察性和互操作性。
📝 摘要(中文)
大型语言模型已将人工智能从孤立的预测服务转变为长时间运行的分布式系统的组成部分,这些系统能够推理、调用工具、检索外部状态、委派任务并代表用户和组织行动。然而,现有的技术生态系统虽然提升了执行效率,却未能提供一个稳定的、与实现无关的操作架构,以管理意图、选择能力、保持授权、控制不确定性、协调运行时行为及重构重要行动的原因。本文提出了Agent操作系统(AOS),作为分布式智能系统的中立参考操作架构,包含控制与治理平面和运行时与协调平面,旨在实现可治理、可靠、可观察和可互操作的智能系统。
🔬 方法详解
问题定义:本文旨在解决当前分布式智能系统缺乏统一操作架构的问题,现有方法在治理意图、授权管理和运行时协调等方面存在不足。
核心思路:提出Agent操作系统(AOS),通过分层架构将控制与治理与运行时协调分开,确保系统的灵活性与稳定性。
技术框架:AOS包含两个主要平面:控制与治理平面负责意图、政策、信任等管理;运行时与协调平面负责代理生命周期、工作流协调、模型和工具路由等。
关键创新:AOS的创新在于提供了一种中立的操作架构,使得不同组件可以高效集成,解决了现有框架在治理和协调方面的局限性。
关键设计:AOS设计了明确的接口以集成平台服务,确保系统的可扩展性和灵活性,同时定义了优化目标和可靠性责任。
🖼️ 关键图片
📊 实验亮点
AOS的设计使得分布式智能系统在治理和协调方面的性能显著提升,能够有效管理复杂的任务和不确定性。尽管具体的性能数据在摘要中未提供,但其架构的灵活性和可扩展性为未来的研究和应用奠定了基础。
🎯 应用场景
该研究的潜在应用领域包括智能助手、自动化工作流和复杂系统的管理。AOS的设计可以帮助开发者构建更可靠的智能系统,提升系统的治理能力和用户信任,推动智能技术的广泛应用。
📄 摘要(原文)
Large language models have transformed artificial intelligence from isolated prediction services into components of long-running, distributed systems that reason, invoke tools, retrieve external state, delegate tasks, and act on behalf of users and organizations. The surrounding ecosystem has responded with agent frameworks, workflow engines, model-serving platforms, memory systems, communication protocols, and observability tools. These technologies improve execution, but they do not provide a stable, implementation-independent operating architecture for governing intent, selecting capabilities, preserving authority across delegation, controlling uncertainty, coordinating runtime behavior, and reconstructing why consequential actions occurred. This paper proposes the Agent Operating System (AOS), a vendor-neutral reference operating architecture for distributed agentic systems. AOS contains two internal planes: a Control & Governance Plane responsible for intent, policy, trust, authority, confidence, auditability, observability, and human oversight; and a Runtime & Coordination Plane responsible for agent lifecycle, workflow coordination, model and tool routing, context and memory coordination, scheduling, traffic management, and runtime assurance. Platform services, Linux or Windows, container runtimes, and physical infrastructure remain outside the AOS boundary and are integrated through explicit interfaces. The paper specifies AOS concepts, invariants, interface objects, optimization objectives, deployment profiles, and reliability responsibilities. It also identifies tradeoffs and unresolved research questions. AOS is not presented as a replacement for existing frameworks or infrastructure; it is proposed as the operating architecture through which heterogeneous components can be composed into governable, reliable, observable, and interoperable agentic systems.