LLM as OS, Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem
Yingqiang Ge, Yujie Ren, Wenyue Hua, Shuyuan Xu, Juntao Tan, Yongfeng Zhang
TL;DR
The paper envisions an AIOS where LLMs act as the system kernel, enabling a new AIOS-Agent ecosystem in which natural language serves as the programming interface and Tools act as devices/libraries. It formalizes a coherent architecture (LLMOS) mapping traditional OS components to LLM-based equivalents, and defines Agents as native applications that can be programmed and orchestrated via NLProg. Through sections on architecture, practical agent applications, multi-agent dynamics, and future directions, the work argues for democratized software development, scalable agent ecosystems, and robust security as core challenges. The proposed roadmap draws strong parallels with the historical evolution of OS design, offering concrete avenues for memory management, tool governance, cross-agent communication, and DSL-based representations of agent plans. The practical impact lies in enabling flexible, user-friendly, and extensible AI-enabled software ecosystems across physical and digital domains.
Abstract
This paper envisions a revolutionary AIOS-Agent ecosystem, where Large Language Model (LLM) serves as the (Artificial) Intelligent Operating System (IOS, or AIOS)--an operating system "with soul". Upon this foundation, a diverse range of LLM-based AI Agent Applications (Agents, or AAPs) are developed, enriching the AIOS-Agent ecosystem and signaling a paradigm shift from the traditional OS-APP ecosystem. We envision that LLM's impact will not be limited to the AI application level, instead, it will in turn revolutionize the design and implementation of computer system, architecture, software, and programming language, featured by several main concepts: LLM as OS (system-level), Agents as Applications (application-level), Natural Language as Programming Interface (user-level), and Tools as Devices/Libraries (hardware/middleware-level). We begin by introducing the architecture of traditional OS. Then we formalize a conceptual framework for AIOS through "LLM as OS (LLMOS)", drawing analogies between AIOS and traditional OS: LLM is likened to OS kernel, context window to memory, external storage to file system, hardware tools to peripheral devices, software tools to programming libraries, and user prompts to user commands. Subsequently, we introduce the new AIOS-Agent Ecosystem, where users can easily program Agent Applications (AAPs) using natural language, democratizing the development of software, which is different from the traditional OS-APP ecosystem. Following this, we explore the diverse scope of Agent Applications. We delve into both single-agent and multi-agent systems, as well as human-agent interaction. Lastly, drawing on the insights from traditional OS-APP ecosystem, we propose a roadmap for the evolution of the AIOS-Agent ecosystem. This roadmap is designed to guide the future research and development, suggesting systematic progresses of AIOS and its Agent applications.