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 4680 条CoworkOS:Scaling Agent Coworkers for Real-world Automation
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, d…
CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents
As coding agents achieve increasingly high success rates on software engineering benchmarks, recent efforts have sought …
SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training
Coding agents solve repository issues through long sequences of exploration, editing, and validation. These trajectories…
Advances in Agentic Computer Graphics
Computer graphics is built on code. Large language model (LLM) agents can now generate graphics code and iteratively ref…
Order-Only On-Policy Distillation
On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. Thes…
Can Large Language Model Agents Learn by Watching Tutorial Videos?
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that …
Democratizing Robot-Use Agents: A Unified Harness with Open Models
Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary …
ODE Policy: Robot Learning via Action Dynamics, Not Actions
Most robot policies, whether trained by imitation learning (IL) or reinforcement learning (RL), map observations to acti…
Nace AI Open-Sources Drex Max v1: A 27B Decision Model That Runs Locally on Apple Silicon
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?
Prediction errors from video world models are often treated as physical surprise, but they can also reflect appearance, …
NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions…
OpenAI、Google、Microsoft、Anthropic 共同支持 robots.txt 统一 AI 训练退出令牌 __usage_ai-training
OpenAI、Google、Microsoft 与 Anthropic 宣布共同支持 robots.txt 中的 __usage_ai-training 令牌，网站一条声明即可统一拒绝 AI 训练抓取，Google 与 Microsoft 计划 2027 年落地。