LLM as OS (llmao), Agents as Apps: Envisioning AIOS, Agents and the AIOS-Agent Ecosystem

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 LLMs 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). In this paper, we begin by introducing the architecture and historical evolution of traditional Operating Systems (OS). Then we formalize a conceptual framework for AIOS through “LLM as OS (LLMAO)”, drawing analogies between AIOS components and traditional OS elements. 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 and developers can easily program Agent Applications (AAPs) using natural language, democratizing the development of and the access to computer software, which is different from the traditional OS-APP ecosystem, where desktop or mobile applications (APPs) have to be programmed by well-trained software developers using professional programming languages. Following this, we explore the diverse scope of Agent Applications. These agents can autonomously perform diverse tasks, showcasing intelligent task-solving ability in various scenarios. We delve into both single agent systems and multi-agent systems, as well as human-agent interaction. Lastly, we posit that the AIOS-Agent ecosystem can gain invaluable insights from the development trajectory of the traditional OS-APP ecosystem. Drawing on these insights, we propose a strategic 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.