操作系统

• 替换

查看 最近的 文章

显示 2025年08月06日， 星期三 新的列表

替换提交 (展示 2 之 2 条目 )

[1] arXiv:2508.02736 (替换) [中文pdf, pdf, html, 其他]

标题： AgentSight：使用eBPF的AI代理系统级可观测性 显示英文标题

标题： AgentSight: System-Level Observability for AI Agents Using eBPF

Yusheng Zheng, Yanpeng Hu, Tong Yu, Andi Quinn

主题： 操作系统 (cs.OS) ; 软件工程 (cs.SE)

现代软件基础设施越来越多地依赖LLM代理进行开发和维护，例如Claude Code和Gemini-cli。 然而，这些AI代理与传统的确定性软件有根本的不同，这对传统的监控和调试构成了重大挑战。 这造成了一种关键的语义差距：现有工具要么通过LLM提示观察代理的高层意图，要么观察其底层操作（例如系统调用），但无法将这两种视角相关联。 这种盲点使得难以区分良性操作、恶意攻击和高成本的故障。 我们引入了AgentSight，这是一个AgentOps可观测性框架，采用混合方法来弥合这一语义差距。 我们的方法，边界追踪，通过eBPF在稳定系统接口处从代理的应用程序代码外部对其进行监控。 AgentSight拦截TLS加密的LLM流量以提取语义意图，监控内核事件以观察系统范围的影响，并使用实时引擎和次级LLM分析在进程边界上因果关联这两个数据流。 这种无仪器化的技术与框架无关，对快速API变化具有鲁棒性，并且性能开销小于3%。 我们的评估表明，AgentSight能够检测提示注入攻击，识别消耗资源的推理循环，并揭示多代理系统中的隐藏协调瓶颈。 AgentSight作为开源项目在https://github.com/agent-sight/agentsight发布。 显示英文摘要

Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a significant challenge to conventional monitoring and debugging. This creates a critical semantic gap: existing tools observe either an agent's high-level intent (via LLM prompts) or its low-level actions (e.g., system calls), but cannot correlate these two views. This blindness makes it difficult to distinguish between benign operations, malicious attacks, and costly failures. We introduce AgentSight, an AgentOps observability framework that bridges this semantic gap using a hybrid approach. Our approach, boundary tracing, monitors agents from outside their application code at stable system interfaces using eBPF. AgentSight intercepts TLS-encrypted LLM traffic to extract semantic intent, monitors kernel events to observe system-wide effects, and causally correlates these two streams across process boundaries using a real-time engine and secondary LLM analysis. This instrumentation-free technique is framework-agnostic, resilient to rapid API changes, and incurs less than 3% performance overhead. Our evaluation shows AgentSight detects prompt injection attacks, identifies resource-wasting reasoning loops, and reveals hidden coordination bottlenecks in multi-agent systems. AgentSight is released as an open-source project at https://github.com/agent-sight/agentsight.

[2] arXiv:2508.03676 (替换) [中文pdf, pdf, html, 其他]

标题： MaLV-OS：重新思考虚拟化云中机器学习的操作系统架构 显示英文标题

标题： MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds

Stella Bitchebe, Oana Balmau

主题： 操作系统 (cs.OS) ; 机器学习 (cs.LG)

大量研究已经采用机器学习（ML）模型来开发学习型操作系统（OSes）和内核。 后者能够根据任务负载动态适应，并动态调整资源（CPU、IO、内存、网络带宽）分配以响应实际用户需求。 这项工作的共同之处在于，它利用ML来改进内核决策。 到目前为止，据我们所知，还没有工作采取相反的方向，即使用操作系统来改进ML。 虽然有些工作提出将系统级优化应用于ML算法，但它们并未针对ML上下文对操作系统进行定制。 为了解决这一限制，我们在本文中采取了一种正交的方法，通过利用操作系统来提高ML模型和算法的性能。 我们探索了通往ML专用操作系统MaLV-OS的路径。 MaLV-OS重新思考了操作系统架构，使其专门针对ML工作负载，尤其是在虚拟化云环境中，这现在被广泛用于运行ML应用。 MaLV-OS设想的架构包括（1）一个微内核Micro-LAKE，它允许内核空间应用程序使用GPU，以及（2）一个MLaaS（ML即服务）子系统，该子系统收集ML模型以帮助Micro-LAKE进行内存管理和CPU调度。 MaLV-OS架构还将模型中对系统敏感的部分卸载到操作系统中，以减轻模型复杂性和编程负担，并加快其执行速度。 最后，MaLV-OS集成了一个开源的GPU虚拟化软件，直接合并到虚拟机监视器中。 为了更多的灵活性，MaLV-OS的愿景是使虚拟机能够动态选择可以提高用户正在运行的模型性能的MLaaS策略。 由于MLaaS被设计为可加载内核模块，MaLV-OS架构使得可以动态地向MLaaS子系统添加新功能。 显示英文摘要

A large body of research has employed Machine Learning (ML) models to develop learned operating systems (OSes) and kernels. The latter dynamically adapts to the job load and dynamically adjusts resources (CPU, IO, memory, network bandwidth) allocation to respond to the actual user demand. What this work has in common is that it utilizes ML to improve kernel decisions. To this day, and to the best of our knowledge, no work has taken the opposite direction, i.e., using OS to improve ML. While some work proposes applying system-level optimizations to ML algorithms, they do not tailor the OS to adapt to the ML context. To address this limitation, we take an orthogonal approach in this paper by leveraging the OS to enhance the performance of ML models and algorithms. We explore the path towards an ML-specialized OS, MaLV-OS. MaLV-OS rethinks the OS architecture to make it specifically tailored to ML workloads, especially in virtualized clouds, which are now widely used to run ML applications. MaLV-OS envisioned architecture includes (1) a micro-kernel, Micro-LAKE, which allows kernel space applications to use the GPU, and (2) an MLaaS (ML as a Service) subsystem that gathers ML models to help Micro-LAKE with memory management and CPU scheduling. MaLV-OS architecture also offloads system-sensitive parts of the models to the OS, to lighten the model complexity and programming, and speed up its execution. Finally, MaLV-OS integrates an open-source GPU virtualization software, merged directly into the hypervisor. For more flexibility, MaLV-OS vision is to enable the virtual machine to dynamically select MLaaS policies that can improve the performance of the model the user is running. Because MLaaS is designed as loadable kernel modules, the MaLV-OS architecture enables the dynamic addition of new capabilities to the MLaaS subsystem.