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Deep Search in Real-World Web Environments
Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web …
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents
Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in…
OpenAI 升级 Chrome 版 ChatGPT 扩展：可读取已打开标签页并接管操作
OpenAI 升级 Chrome 版 ChatGPT 扩展：支持读取已打开标签页提供针对性回答，Work 模式可直接操控标签页操作，与 Gemini、Copilot 争夺浏览器侧边栏入口。
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight in…
IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify wh…
NVIDIA Releases Nemotron 3.5 Super VL, a 120B Open Multimodal Agent Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models
Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inference c…
Nvidia's Nemotron 3.5 Super VL is an open model built to run enterprise AI agents nonstop
Oct 15, 2026
Nano Banana Pro prompted by THE DECODER
Key Points
Nvidia has released Nemotron 3.5 Super VL, an open multi…
Google wants Gemini 4 Argon to be the only AI model robots need
Oct 15, 2026
Google Deepmind
Key Points
Gemini 4 Argon is Google's attempt at a single AI model that controls robots, ge…
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeat…
Muse Spark Open is Meta's answer to Qwen, GLM, and Kimi in the open-weight race
Oct 15, 2026
After its Llama series, Meta is returning to open-weight territory with Muse Spark Open.** Meta calls it th…
Be There for the Beginning: Celebrate the Launch of NVIDIA RTX Spark
A new beginning for Windows PCs starts tomorrow with the launch of NVIDIA RTX Spark — one PC built for creators, gamers …