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OpenAI launches Decisions API that reduces complex evaluations to yes, no, or pick one
Oct 7, 2026
OpenAI announced two updates to its API platform.** The new Decisions API evaluates text, images, or both, r…
CADFather：通过协同工具调用实现自主CAD重建
CADFather是一个自主智能体系统，由视觉语言助手协调多种学习与算法工具，从3D网格恢复可编辑的参数化CAD程序。
Personal-Agent Mediated Recommendation with Cross-Platform User History
Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a pe…
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement a…
SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation
Language-guided panoramic video generation benefits various downstream applications, such as interactive 3D scene explor…
苹果突发收紧 Mac 权限，全是 AI 惹的祸
macOS，开始对 Personal Agent「关门」了。
10 月 2 日，苹果发出一则简短的公告，宣布将会在后续版本收紧在 macOS 上存在多年的「完全磁盘访问」（Full Disk Access, FDA）高级权限：
一些开发者正…
Building a Streaming Robotics Learning Pipeline Using NVIDIA Cosmos3-DROID
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station
Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they can…
Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents
A central capability of embodied agents is to accomplish complex objectives through sequences of interdependent tasks. Y…
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, …
Reflection AI Introduces Beam: A 501B Open-Weight MoE Model With 23B Active Parameters for Coding and Agentic Workloads
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on …