11-19 更新 实时
首页/ 算力/ 正文

OpenShell 架构如何保障与治理 AI 智能体

算力 来源:NVIDIA Developer 2026-11-06 05:29 0 阅读 机器翻译
OpenShell 架构如何保障与治理 AI 智能体

自主智能体可以在复杂任务上持续工作数小时,访问文件、工具、互联网,并生成其他智能体与之协作。在长时间跨度内执行复杂任务会导致复合风险:智能体可能会下载代码、构建新工具、请求额外权限,并触及更多底层基础设施。智能体的行动路径是在它们工作时确定的……

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(How NVIDIA OpenShell Reference Architecture Secures and Governs AI Agent Workloads at Scale)
Autonomous agents can work for hours on complex tasks, accessing files, tools, the internet, and spawning other agents to collaborate with. Executing complex...

Autonomous agents can work for hours on complex tasks, accessing files, tools, the internet, and spawning other agents to collaborate with. Executing complex tasks over long time horizons leads to compounding risk: the agents may download code, build new tools, request additional privileges, and touch more of the underlying infrastructure. The agents’ action paths are determined as they work…

Source

正文保留英文原文,标题与摘要由机器翻译。

本文由采集器自动同步

原文发布于 NVIDIA Developer(How NVIDIA OpenShell Reference Architecture Secures and Governs AI Agent Workloads at Scale),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗