LLM-based intelligent agents face significant deployment challenges, particularly related to resource management. Allowing unrestricted access to LLM or tool resources can lead to inefficient or even potentially harmful resource allocation and utilization for agents. Furthermore, the absence of proper scheduling and resource management mechanisms in current agent designs hinders concurrent processing and limits overall system efficiency. To address these challenges, this paper proposes the architecture of AIOS (LLM-based AI Agent Operating System) under the context of managing LLM-based agents. It introduces a novel architecture for serving LLM-based agents by isolating resources and LLM-specific services from agent applications into an AIOS kernel. This AIOS kernel provides fundamental services (e.g., scheduling, context management, memory management, storage management, access control) for runtime agents. To enhance usability, AIOS also includes an AIOS SDK, a comprehensive suite of APIs designed for utilizing functionalities provided by the AIOS kernel. Experimental results demonstrate that using AIOS can achieve up to 2.1x faster execution for serving agents built by various agent frameworks. The source code is available at https://github.com/agiresearch/AIOS.
From Commands to Prompts: LLM-based Semantic File System for AIOS
Dalian University of Technology（大连理工大学）；Rutgers University（罗格斯大学）；Purdue University（普渡大学）；New Jersey Institute of Technology（新泽西理工学院）；EPFL（洛桑联邦理工学院）；University of Minnesota（明尼苏达大学）
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Technology Sydney（悉尼科技大学）；Northeastern University（东北大学）；University of Liverpool（利物浦大学）
EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents
National University of Singapore（新加坡国立大学）；The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）；KAUST（阿卜杜拉国王科技大学）；University of Oxford（牛津大学）；Tsinghua University（清华大学）；Nanjing University（南京大学）；Fudan University（复旦大学）
EEG-SpikeAgent: Agentic Closed-Loop Program Synthesis for Automated EEG Spike Detection
Dept. of Brain and Cognitive Sciences, Massachusetts Institute of Technology（脑科学与认知科学系，麻省理工学院）；Dept. of Neuroscience, University of California, Berkeley（神经科学系，加州大学伯克利分校）；Dept. of Neurology and Neurologic Sciences, Stanford University（神经病学与神经科学系，斯坦福大学）；Weill Institute of Neurology and Neurosciences, University of California, San Francisco（Weill神经医学研究所，加州大学旧金山分校）；University of California, San Francisco（加州大学旧金山分校）
We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanjing University（南京大学）；Institute of Automation, CAS（中国科学院自动化研究所）；Nanyang Technological University（南洋理工大学）
SurgBox: Agent-Driven Operating Room Sandbox with Surgery Copilot
CAIR, HKISI, CAS（中国科学院香港中文大学信息安全研究所智能计算研究中心）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统实验室）；Peking Union Medical College Hospital（北京协和医院）
OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
Zhejiang University（浙江大学）；Fudan University（复旦大学）；OPPO AI Center（OPPO AI中心）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）；The Hong Kong Polytechnic University（香港理工大学）
TuneAgent: Agentic Operating System Kernel Tuning with Reinforcement Learning
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Nanyang Technological University（南洋理工大学）
