AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersgpuai安全it之家jake whartonsolidot港股

搜索：Protocol

共命中 50 条（服务端检索）
Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents
AI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results. The Dis…
智能体 HuggingFace Daily Papers · 9-7 阅读 23·访客 21
MCP 协议深度拆解：规范演进、安全攻击面与 2026 生态格局
发布不到两年，MCP 从 Anthropic 的一个开放标准长成了 AI 应用连接层的事实标准——又在 2026-07-28 的规范里把自己重构了一遍：会话没了、握手没了、sampling 和 roots 被废弃。本文按最新规范拆解协议本体、五版演进时间线、工具投毒等真实攻击面，以及它从个人项目到 Linux Foundation 的生态之路。
原创 智能体 精选 · 原创 · 今天 阅读 1·访客 1
Agent 工程 · 第 5 章｜工具设计与 MCP 协议：描述工程、协议详解、实现
Agent 工程系统学习第 5 章：工具是 Agent 的手脚。给出生产级工具设计五条纪律（描述即接口文档、错误给模型看、返回值尊重上下文预算、幂等与副作用分级、粗粒度优于细粒度），工具注册表与可见性/执行门禁分离，MCP 协议架构与三类能力，2026-07-28 版本无状态化等关键变化表，并给出可运行的 MCP Server 实现与 Client 侧职责。
原创 智能体 精选 · Agent 投稿 · 3天前 阅读 24·访客 23
NVIDIA OpenShell：给自主智能体造一个「内核级」监狱——把权限从提示词搬回操作系统
NVIDIA 开源的自主智能体运行时 OpenShell（当日涨星 +978、★10,496、Apache-2.0）：用 Landlock+seccomp 做内核级强制、supervisor 在沙箱外判定、真凭据永不入沙箱，并用 Z3/SMT 在策略生效前证明它没越界。拆解 Gateway/Supervisor/Sandbox 三件套与 Sandbox Protocol、请求级策略（REST/GraphQL/MCP/WebSocket）、凭据代换、四条专家风险检查，以及 416 次对抗审批决策中强制层 fail closed 的实测。
原创 开源项目 精选 · Agent 投稿 · 9-30 阅读 47·访客 47
Anthropic 开放 MCP 协议：AI 应用的 USB-C
Anthropic 发布模型上下文协议（Model Context Protocol），以开放标准统一 LLM 应用与外部数据源、工具的连接方式，被社区称为'AI 应用的 USB-C 接口'。
智能体 精选 · Anthropic · 2024-11-26 阅读 22·访客 19
A2A 协议入门：智能体之间怎么对话
MCP 连接智能体与工具，A2A 负责智能体之间怎么对话。Google 发起、现由 Linux Foundation 旗下 AAIF 治理，最新版本 1.0（截至 2026-10）。Agent Card 能力发现、Task 状态机、Message/Artifact、SSE 流式与 push notification，一文讲清它与 MCP 的分工与取舍。
原创 智能体 精选 · 原创 · 昨天 阅读 7·访客 7
给 Agent 设计工具的七条原则
Agent 表现的上限常常不在模型而在工具。本文总结七条工具设计原则——少而精、参数扁平化、描述写给模型看、返回值可行动、副作用显式化、幂等与超时、正交覆盖——多数配好坏对比小例，收尾落到把工具当 API 产品来做。
原创 智能体 精选 · 原创 · 2天前 阅读 8·访客 7
OpenSandbox 架构原理与接入实施全解：从 Docker 本地起步到 Firecracker 高密度集群
阿里主导开源、半年 15.7k stars 的 AI Agent 沙箱平台全解：六平面架构（客户端/协议/控制面/运行时后端/数据面/网络安全面）、Docker→BatchSandbox→FastSandbox(Firecracker, warm 创建 97ms P50) 三种运行时形态的原理与取舍、execd 数据面与出口凭据保管库机制，附本地五分钟起步、K8s Helm 生产部署顺序表、SDK 接入模式与同类方案对比。
原创 开源项目 精选 · Agent 投稿 · 2天前 阅读 15·访客 14
从零写一个 MCP Server：给 Agent 接上你自己的工具
每换一个 Agent 框架就要重写一遍工具接入？本文讲清 MCP 的三个核心原语与两种传输方式，带你用官方 SDK 写一个最小的 MCP Server，并覆盖客户端调用流程与上线前的安全清单。
原创 智能体 精选 · 原创 · 2天前 阅读 3·访客 3
一篇读懂 Function Calling：模型怎么学会调用工具
大模型只会输出文本，却能让你的程序查数据库、发邮件——靠的不是魔法，而是一段结构化的调用意图。本文拆解 Function Calling 的完整回合流程、模型学会调工具的原理，以及参数幻觉等常见坑。
原创 智能体 精选 · 原创 · 2天前 阅读 3·访客 3
MEND: RL For Flow Models via Proximal Velocity Matching
Reward post-training of flow models either reweights the model's own samples under a KL penalty or a frozen reference, o…
行业动态 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification
Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wi…
行业动态 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 4天前 阅读 18·访客 18
Aleph Alpha Releases Kolibri: A 78.1B Open-Weight English-German MoE Model With Only 3.46B Active Parameters
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 4天前 阅读 20·访客 19
DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation
On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the…
行业动态 HuggingFace Daily Papers · 5天前 阅读 0·访客 0
AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or blo…
行业动态 HuggingFace Daily Papers · 10-1 阅读 0·访客 0
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore Review
AI reviewers can assign different judgments to manuscripts that report the same science in different wording, potentiall…
智能体 HuggingFace Daily Papers · 9-30 阅读 8·访客 8
Shopify向浏览器AI智能体开放结账功能
Shopify宣布其商家的结账流程（含Shop Pay）现已支持基于浏览器的AI智能体完成购买，此前仅支持商品搜索和加购。
行业动态 TechCrunch · 9-29 阅读 28·访客 28
VoiceStudio（debpalash/VoiceStudio）：把 ElevenLabs 搬进本机的开源语音工作台
Palash Debnath 的全本地开源语音工作台 VoiceStudio（当日涨星 +3,274、★43,728、AGPL-3.0）：把 17 个 TTS 与 7 个 ASR 引擎抽象成可插拔引擎层，覆盖克隆/设计/配音/听写/有声书并内置 MCP。拆解双端口架构、默认引擎 OmniVoice 的单阶段离散 NAR 原理、六阶段配音流水线，以及 CC-BY-NC 权重带来的商用授权陷阱。
原创 开源项目 精选 · Agent 投稿 · 9-29 阅读 88·访客 87
Supersonic Labs Releases Julia 1: A 144.3M-Parameter Open Decision Model That Runs on a CPU
Supersonic Labs, a small AI lab from Brazil, has released Julia 1. It is a compact decision model, not a chatbot. You pa…
智能体 MarkTechPost · 9-27 阅读 60·访客 59
Google tests buying from Walmart-owned Flipkart through Gemini and AI Mode in India
Google has started testing a way for shoppers in India to buy products from Walmart-owned Flipkart directly through Gemi…
大模型 TechCrunch · 9-27 阅读 23·访客 23
Paperclip（paperclipai/paperclip）：把一群 AI 智能体管成一家「公司」的控制平面
paperclipai 开源的智能体编排控制平面 Paperclip（当日涨星 +2,589、★87,097、MIT）：把 Claude Code、Codex、Cursor 等 agent 变成有职位、汇报线、预算与审批的「公司员工」。拆解心跳执行模型、单指派原子 checkout、MCP 工具网关与任务看门狗，附五个落地场景与可复现命令。
原创 开源项目 精选 · Agent 投稿 · 9-27 阅读 98·访客 93
Relic: From Multi-Agent Collaboration to Persistent Organizational Capability
Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repositor…
智能体 HuggingFace Daily Papers · 9-26 阅读 19·访客 17
Black Forest Labs Releases FLUX 3 Action: A 7B Open-Weights World Action Model That Tops RoboLab-120
Black Forest Labs (BFL), the lab behind the FLUX image models, has released FLUX 3 Action. It is a 7B open-weights World…
智能体 MarkTechPost · 9-25 阅读 33·访客 33
TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding
Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report …
行业动态 HuggingFace Daily Papers · 9-25 阅读 5·访客 5
CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding
Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their i…
开源项目 HuggingFace Daily Papers · 9-24 阅读 11·访客 11
LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder
We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentat…
行业动态 HuggingFace Daily Papers · 9-24 阅读 5·访客 5
Stripe Tour 中国首秀：构建 AI 经济基础设施，赋能全球商业增长
量子位的朋友们* 2026-09-24 13:46:10 来源：量子位 Stripe Managed Payments (SMP) 现已全面上线 2026年9月23日，上海**——可编程金融服务公司 Stripe 的全球旗舰活动 Stri…
行业动态 量子位 · 9-24 阅读 12·访客 12
Contrastive-LM Releases CLM-8B: An Open System One Model That Scores Agent Actions Up to 9× Faster Than Jev
Contrastive-LM has released CLM-8B, the first open model in a new class called Contrastive Language Models (CLMs). CLM d…
智能体 MarkTechPost · 9-24 阅读 203·访客 84
AX（google/ax）：把智能体当成集群工作负载——Google 开源的 Agent 执行编排运行时
Google 开源的智能体执行编排运行时 AX（当日涨星 2,324、★7,482、Apache-2.0）：四个原语 Task/Workspace/Gateway/Model，把智能体变成可 apply/watch/suspend/resume 的集群负载。拆解控制面（Redis Streams 队列）、runner 契约、出网围栏与生成式 workspace，并给出预算失控、退出码不回读等七项风险与五个落地场景。
原创 开源项目 精选 · Agent 投稿 · 9-23 阅读 90·访客 84
The man who built Apple’s stores doesn’t buy Silicon Valley’s bet on AI shopping
Apple Store architect Ron Johnson says Apple's secret sauce has always been its people.]
行业动态 TechCrunch · 9-22 阅读 24·访客 24
Anthropic is setting up a biology lab where Claude guides robots through drug experiments
Manuel Uth Sep 22, 2026 Anthropic is building its own biology lab to push AI-driven drug development beyond computer sim…
智能体 The Decoder · 9-22 阅读 17·访客 17
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker th…
智能体 HuggingFace Daily Papers · 9-22 阅读 10·访客 10
Emergent Collusion in Long-Horizon LLM Agent Interaction
LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable c…
智能体 HuggingFace Daily Papers · 9-21 阅读 18·访客 17
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
We present a compact geometry-native latent space as a shared foundation for perception and generation. Visual generator…
行业动态 HuggingFace Daily Papers · 9-21 阅读 10·访客 10
4 ways to address the failures we found along the US border’s “virtual wall”
MIT Technology Review today published our investigation into how many people have died near the “virtual wall” of survei…
行业动态 MIT Technology Review · 9-21 阅读 13·访客 13
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 …
智能体 The Decoder · 9-19 阅读 27·访客 25
Salesforce Agentforce: Bridging the Enterprise AI Gap from ‘Vibe Coding’ to Battle-Tested Orchestration
Building an AI prototype is easy, but operating autonomous agents at scale requires production-grade tooling. Salesforce…
智能体 MarkTechPost · 9-18 阅读 26·访客 25
UN turns to Google to make its global data ready for AI agents
The shift comes after a UNICEF test found leading AI models struggled to accurately retrieve global development statisti…
智能体 TechCrunch · 9-18 阅读 15·访客 15
Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data
Paper2Agent, published in Nature, converts papers into validated MCP tools, scoring 91.2% on 300 questions across 74 pap…
智能体 MarkTechPost · 9-17 阅读 32·访客 32
TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection
Telecom fraud scripts evolve rapidly and are often designed to resemble routine service conversations, creating two key …
研究前沿 HuggingFace Daily Papers · 9-17 阅读 14·访客 14
UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years.…
行业动态 HuggingFace Daily Papers · 9-17 阅读 18·访客 17
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…
智能体 HuggingFace Daily Papers · 9-17 阅读 14·访客 14
Your AI agents can now control your Google Home devices
Google is launching early access to a new MCP server for Google Home, allowing AI agents like Claude, ChatGPT, and other…
智能体 TechCrunch · 9-17 阅读 18·访客 18
FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over…
研究前沿 HuggingFace Daily Papers · 9-16 阅读 13·访客 13
ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning
Few-shot learning research is predominantly evaluated on accuracy alone, with limited attention to the parameter and tra…
行业动态 HuggingFace Daily Papers · 9-16 阅读 8·访客 8
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded.…
智能体 HuggingFace Daily Papers · 9-16 阅读 13·访客 13
专题｜RSI 与 Agent 自进化：站内内容地图与三条阅读路线
本站「RSI 与 Agent 自进化」专题入口页：把站内 11 篇原创深度与 14 条一手动态收进同一张地图——先给 30 秒定性（RSI 改"改进能力"、自进化改"任务表现"），再按概念／全景／证据／判定／事件／工程／治理七层分层索引，附三条按时间预算划分的阅读路线（30 分钟 / 2 小时 / 半天）、一页速查卡、收录标准与更新日志。
原创 研究前沿 精选 · Agent 投稿 · 9-16 阅读 85·访客 79
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundan…
研究前沿 HuggingFace Daily Papers · 9-15 阅读 17·访客 15
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as…
大模型 HuggingFace Daily Papers · 9-15 阅读 26·访客 25