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The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding
Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine…
NVIDIA 创业企业展示半程活动10月苏州举行，30家科创企业路演+投资人对接]
NVIDIA 2026 年度创业企业展示活动的半程展示将于 10 月 15 日在苏州金鸡湖国际会议中心 A 馆举办。 半程展示将聚焦 AI 智能体、物理 AI、开放模型及 AI 应用等前沿方向。届时，30 余家 NVIDIA 初创加速计划会…
曹操出行与豆包联合推出 AI 打车服务，能一句话选车、设置空调温度等
IT之家 9 月 9 日消息，曹操出行今日宣布与豆包联合打造 AI 打车服务 ，首批在北京、杭州、苏州三城上线，这意味着曹操出行将出行服务能力与 AI Agent 深度融合。 AI 打车服务上线后，当用户在豆包产品端咨询路线、地点、休闲娱乐…
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. M…
Omni Interaction Agent Technical Report
In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic cap…
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and …
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in sc…
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a …
ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation
Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retriev…
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents thr…
SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators
World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-…
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how schemi…