深度研究｜Agent 沙箱技术核心架构方案：从 microVM 隔离到硬件加速快照的七层设计
基于视频《为什么沙箱成了 AI 圈最卷的新基建》的深度延伸调研。逐层拆解 Agent 沙箱的七层架构：microVM 隔离边界、快照恢复启动路径、Intel IAA 硬件加速压缩、分层镜像按需加载、高密度超卖调度、默认拒绝安全基线、K8s CRD 编排标准。锚定 Firecracker NSDI'20、Sabre OSDI'24、DeepSeek DSec arXiv 2609.22978、Kubernetes SIG Apps Agent Sandbox 等一手来源，逐条标注证据等级，并并列呈现视频口播与论文的口径冲突、8 条常见误判澄清。
阅读全文 →
全部文章
ARCHIVE 共 745 条GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece
Oct 15, 2026
NBPro prompted by THE DECODER
A new benchmark shows the best AI agents can solve theoretical physics calcul…
Figma announces new features to define how agents work on its platform
Design platform Figma announced a new Markdown-based editor to help define a company’s design, bring in design and code …
Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completi…
AI agents are coming to Rivian’s cars
Rivian recently rolled out an AI assistant that lets drivers and passengers interact with the company’s electric vehicle…
Meet Grok Voice 3.0: SpaceXAI Voice Agent Model Ranks #1 on Artificial Analysis
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
Researchers tracked down a rogue fleet of Chinese AI agents in the wild and actually talked to it
Oct 14, 2026
Nano Banana Pro prompted by THE DECODER
Researchers have, likely for the first time, tracked down a "rogue …
CopilotKit Releases CLiF: A Continual Learning Platform That Turns Agent Traces and User Actions into Skills, Evals, and Fine-Tuning Data
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Video scene graph generation (VidSGG) aims to capture objects and their evolving relationships in videos. This requires …
SwarmRSI：通过进化的科学智能体群实现递归自我改进
SwarmRSI 是一个让科学智能体群实现递归自我改进的框架，提出反馈引导的群体变异（Feedback-Guided Swarm Mutation）来利用其他智能体的实验反馈修正假设与实现，并引入互补群体重组（Complementary Swarm Recombination）复用对其他智能体有用的组件。
European Cities Deploy NVIDIA-Powered AI Agents to Run Smarter Urban Operations
Keeping a city running means making decisions that affect residents every day — from when to repair a road to how to use…
AI 代理链上支付激增：已产生 1.38 亿美元加密交易，美国占支出大头
Chainalysis 数据显示，AI 代理已通过 Coinbase 的 Base 区块链完成 1.38 亿美元加密支付，用于购买服务、数据和模型访问代币。