立场论文：是时候通过自进化操作系统层虚拟化基础模型了
Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
浏览论文内容
中文总结 AI 辅助
本文提出基础模型操作系统（FMOS），通过虚拟化FM交互解决智能体系统碎片化问题，实现行为可移植与治理稳健，并自进化地决定干预时机。
中文摘要 AI 辅助
AI应用已从单一、单体式的基础模型（FM）转向复合智能体系统。然而，当今的技术栈仍然支离破碎：即使协议（如MCP、A2A）简化了工具/智能体连接，每个框架仍嵌入了用于状态、记忆、预算和护栏的隐式运行时，使得行为不可移植且治理脆弱。这类似于操作系统出现之前的计算时代，当时每个程序都重新实现基本服务。本立场论文认为，该领域现在需要一个基础模型操作系统（FMOS）——一个系统层，将FM交互虚拟化，类似于虚拟机抽象物理硬件的方式，给应用程序以专用、可信的FM实例且能力几乎无限的错觉。在内部，FMOS跨记忆层级编排知识、模型选择和资源分配，以及验证和策略执行。如同人脑在快速直觉与缓慢深思之间切换，FMOS学习何时干预以及何时让推理直接进行，并根据操作经验持续调整其策略。
英文摘要
AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as protocols (e.g., MCP, A2A) ease tool/agent connectivity, each framework embeds an implicit runtime for state, memory, budgets, and guardrails, making behavior non-portable and governance brittle. It mirrors computing before operating systems, when every program re-implemented basic services. This position paper argues that the field now needs a Foundation Model Operating System (FMOS) -- a system layer that virtualizes FM interactions analogous to how virtual machines abstract physical hardware, giving applications the illusion of dedicated, trustworthy FM instances with effectively unbounded capabilities. Internally, the FMOS orchestrates knowledge across memory tiers, model selection and resource allocation, and verification and policy enforcement. Like the human brain switching between fast intuition and slow deliberation, the FMOS learns when to intervene and when to let inference proceed directly and continuously adapting its policies based on operational experience.
发表机构
- Hewlett Packard Enterprise（慧与公司）
- University of Chicago（芝加哥大学）
- Argonne National Laboratory（阿贡国家实验室）
机构由 AI 辅助整理，请以论文原文为准。
