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Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
When retrieved evidence contradicts an agent's prior beliefs, does it revise its answer, acknowledge uncertainty, or per…
BrickBench: Evaluating Agentic Brick Design
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with…
微软发布 VS Code v1.141：清理“僵尸”Agent 会话等
IT之家 10 月 8 日消息，微软昨日（10 月 7 日）更新推出 Visual Studio Code 1.141，本次更新聚焦 AI 智能体（Agent）工作流管理，**重点改进会话存储清理、跨平台沙盒安全、多会话并排布局，以及多 G…
Robot data startup Mecka AI nabs $60M from Sequoia
Mecka AI, a startup that collects and analyzes human motion data to train humanoid robots and other kinds of robots, ann…
微软描绘 Autopilot 全新蓝图：让 Windows AI 从“回答问题”走向“执行任务”
IT之家 10 月 8 日消息，微软今天召开 Surface 新品发布会，现场展示 Autopilot 未来方向。根据其设想，这款智能体将让 Windows AI 进一步实现自主化执行任务。
在微软的设想下，Autopilot 不再只是根据…
微软重点介绍 MXC SDK，为 AI 智能体提供受控执行环境
IT之家 10 月 8 日消息，据科技媒体 The Verge 报道，微软今天在 Windows 与 Surface 发布会重点介绍 MXC（ Microsoft Execution Containers） SDK，将其称为 Windows…
Teen's AI-guided mountain hike ends with a helicopter rescue and a lesson in common sense
Manuel Uth
Oct 8, 2026
A 16-year-old had to be airlifted off a dangerous rock face on Crown Mountain near Vancouver afte…
适配大屏：Meta 推出 iPad 版 Muse AI 智能体
IT之家 10 月 7 日消息，Meta 现已将 Muse AI 智能体适配苹果 iPad 平台，**同时新增 Canva、Dropbox、Figma、QuickBooks、GitHub、Klaviyo、Zoom 等连接器**。
IT之家了…
Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation
This work examines the transfer of a co-evolved communication mechanism between two robotic agents from a discrete two-d…
OpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots
OpenAI just made one of its biggest bets yet on what comes after the chatbot. Now, the person leading that product is co…
MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent
Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matc…
Coding-Agent Benchmarks Should Match Their Users' Task Flows
The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent s…