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 →
最新文章
LATEST 共 4850 条Diffusion Language Models Change Speed Across Tasks and Languages
Diffusion language models can write several tokens in one forward pass, and they decide during generation how many passe…
MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflows
Medical workflows often require multiple interdependent analyses, but existing specialist and generalist AI models are n…
Who Takes the Lead? Model Ability and Task-Conditioned Collaboration with Humans
As language-model agents grow more capable, they can carry more of a task without asking anyone for help. Falling relian…
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing ap…
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 API 疑现三个未公布模型：aurora-red/green/blue-alpha 短暂露面后被移除
10 月 18 日，aurora-red/green/blue-alpha 三个无文档、无定价的模型标识短暂出现在 OpenAI API 中随后被移除，测试者推测与图像生成有关。
DeepSeek 升级 V4.1 Flash 编程模型并开放搜索 API：千次调用 5 元，按成功计费
DeepSeek 将 V4.1 Flash 更新至 1017 版，同步向公众开放 Search 与 Fetch 两个接口，定价均为 5 元/千次，按成功调用计费。
TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models
Large-scale action pretraining equips Embodied Foundation Models (EFMs) with strong manipulation capabilities, with part…
Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
Large language models need effective ways to acquire and use external knowledge beyond what they retain from pretraining…
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。
Anthropic 私下向美国国会推介自拟前沿 AI 安全法案草案，拟设政府干预门槛
据报道，Anthropic 已拟定前沿 AI 安全法案草案并私下向美国国会议员推介，拟设政府干预门槛：可能造成超 10 亿美元损失或 50 人以上死伤时方可阻止模型发布。