The integration and deployment of large language model (LLM)-based intelligent agents have been fraught with challenges that compromise their efficiency and efficacy. Among these issues are sub-optimal scheduling and resource allocation of agent requests over the LLM, the difficulties in maintaining context during interactions between agent and LLM, and the complexities inherent in integrating heterogeneous agents with different capabilities and specializations. The rapid increase of agent quantity and complexity further exacerbates these issues, often leading to bottlenecks and sub-optimal utilization of resources. Inspired by these challenges, this paper presents AIOS, an LLM agent operating system, which embeds large language model into operating systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI. Specifically, AIOS is designed to optimize resource allocation, facilitate context switch across agents, enable concurrent execution of agents, provide tool service for agents, and maintain access control for agents. We present the architecture of such an operating system, outline the core challenges it aims to resolve, and provide the basic design and implementation of the AIOS. Our experiments on concurrent execution of multiple agents demonstrate the reliability and efficiency of our AIOS modules. Through this, we aim to not only improve the performance and efficiency of LLM agents but also to pioneer for better development and deployment of the AIOS ecosystem in the future. The project is open-source at https://github.com/agiresearch/AIOS.

翻译：基于大语言模型（LLM）的智能体集成与部署面临诸多挑战，制约了其效率与效能。这些问题包括：智能体对LLM请求的次优调度与资源分配、智能体与LLM交互过程中上下文维持的困难，以及整合具备不同能力与专长的异构智能体时固有的复杂性。智能体数量与复杂度的快速增长进一步加剧了上述问题，常常导致资源瓶颈与非优利用。受这些挑战启发，本文提出AIOS——一种LLM智能体操作系统，将大语言模型嵌入操作系统作为其“大脑”，实现“有灵魂”的操作系统——这是迈向通用人工智能（AGI）的重要一步。具体而言，AIOS旨在优化资源分配、促进智能体间上下文切换、支持智能体并发执行、提供工具服务并维护访问控制。我们阐述了该操作系统的架构，概述了其旨在解决的核心挑战，并给出了AIOS的基本设计与实现。对多智能体并发执行的实验验证了AIOS各模块的可靠性与效率。通过此项工作，我们不仅致力于提升LLM智能体的性能与效率，更为未来AIOS生态系统的更好开发与部署开创先河。该项目已开源，地址为 https://github.com/agiresearch/AIOS。