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 864 条EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
Vision-language-action (VLA) models map visual observations and language instructions directly to robot actions, but lon…
Using Grounded Theory for Agent Behavior Analysis at Scale
Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, …
Dr. Claw: An AI Scientist Workspace for Vibe Research
Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, y…
AgenticGen: Reward-Guided Agentic Video Generation for Advertising
Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose …
Scaling Automatic Research Agents via World Models
Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring …
AgentKernel: The Trust-Native Agentic Operating System
Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instruction…
Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?
Repository-level coding benchmarks have become the standard for evaluating coding agents, yet they inherently suffer fro…
Flask 之父撰文力荐 Pi：极简 Agent 的设计哲学
Armin Ronacher 发表《Pi: The Minimal Agent Within OpenClaw》，系统阐述了 Pi 框架'四个工具 + 最短系统提示词'的极简主义 Agent 设计观。
OpenClaw 刷屏：个人 AI 助理的开源引爆点
Peter Steinberger 的开源个人智能助理项目（前身 ClawdBot / MoltBot）更名为 OpenClaw 并刷屏科技圈，7×24 小时待命的'电子员工'形态引发全网部署热潮。
Manus 邀请码刷屏：通用 Agent 的中国时刻
中国团队 Monica 发布通用智能体产品 Manus，以'Less Structure, More Intelligence'理念实现任务全自动执行，在 GAIA 基准取得 SOTA 表现，一码难求。
Claude Code 发布：终端里的编程智能体
Anthropic 随 Claude 3.7 Sonnet 推出命令行编程智能体 Claude Code，可自主读写代码库、运行测试与提交修改，开启'终端 Agent'产品形态。
Anthropic 开放 MCP 协议：AI 应用的 USB-C
Anthropic 发布模型上下文协议（Model Context Protocol），以开放标准统一 LLM 应用与外部数据源、工具的连接方式，被社区称为'AI 应用的 USB-C 接口'。
← 上一页
第 72 / 72 页 · 共 864 条