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 843 条One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
Repository-level software engineering (SWE) comprises heterogeneous task categories, whose progress under pooled agentic…
微软花费 12 万美元 token 将 Copilot 运行时移植到 Rust 语言]
微软利用使用 GPT-5.6 Sol 和 Claude Opus 4.8 的 AI 智能体、历时 14.5 周，花费 12 万美元 token 将 Copilot 运行时从 TypeScript 语言移植到 Rust 语言。该项目采用逐个更…
中国电信开源首个全栈国产轻量级智能体大模型 Xing4.0-29B-A4B
IT之家 9 月 19 日消息，中国电信于 9 月 17 日发布新一代星辰大模型 Xing4.0-29B-A4B，该模型总参数量 29B，激活参数仅 4B，原生支持 256K 上下文，可扩展至 512K， 是国内首个基于国产算力与国产框架完…
GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark
Leading AI models usually attempt dangerous tasks rather than refuse them when controlling a robot, according to the Rob…
Transferring the Intelligence of VLMs to Robotic Control
Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in e…
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for th…
Qwen3.8-Omni-Flash undercuts Google's Gemini Flash pricing while matching its multimodal benchmarks
Qwen3.8-Omni-Flash is Qwen's first multimodal model designed for AI agents. It processes audio and video together and in…
U.S. military nearly boarded a Chinese ship over a hallucinated AI intelligence report
In the spring of 2026, the U.S. military came within minutes of boarding a Chinese ship because an AI chatbot falsely fl…
Self-Organizing Agent Teams Learn to Reason Together
Collective intelligence depends not only on what team members know, but also on how they organize their work. When the s…
Unity launches official plugins for Claude Code and OpenAI Codex to stop AI agents from using outdated tutorials
Unity has released official plugins for Claude Code and OpenAI's Codex. The article Unity launches official plugins for …
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large langua…
Google’s new ‘CC’ is an AI agent that helps families run their households
Google is refocusing its CC AI agent on household coordination, letting families share emails, schedules, and tasks so t…