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Self-Evolving Search Index
Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. …
Iceland-based Treble raises $18 million for its voice simulation platform
Treble's voice simulation platform is used by voice AI model developers, AI wearable, and robotics companies]
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering …
Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy
Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on la…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work ha…
AI agent swarms are a massive waste of tokens with zero quality gain, says OpenAI Codex developer
OpenAI Codex developer Eric Provencher warns that running more than two parallel sub-agents almost always burns tokens w…
网易有道周枫：AI能力竞争，正在进入「Model + Agent + Workflow」时代，网易有道AI Open Day展示AI时代“有道解法”
9月16日，网易有道「NEXT，AGENT｜有道AI Open Day」在北京举办。]
AI labs want in-house auditors — but maybe they should shut the front door first
There may be a simpler and more effective fix for rogue agents, hiding in plain sight.]
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major…
EU president warns AI agents "escaping their environment" are just a preview of what's coming
Ursula von der Leyen plans to invite the major frontier labs to talks and use the AI Act to help set global AI safety st…
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation
Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as assis…
央企做了个通用Agent，直接杀进IDC实测前三！
中国电信，TeleAgent]