AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersai安全gpujake whartonit之家solidot港股

搜索：computer-use

共命中 50 条（服务端检索）
一篇读懂 Computer Use：让大模型亲手操作你的电脑
API 覆盖不了的世界还剩一大半——政务系统、遗留软件、没有开放接口的网页。Computer Use 让模型像人一样看屏幕、动鼠标、敲键盘，把「剩下的一大半」变成智能体的疆域。本文拆解它的感知-行动循环、两条技术路线、OSWorld 成绩单与提示注入的真实风险。
智能体 精选 · 原创 · 10-24 阅读 100·访客 98
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…
智能体 HuggingFace Daily Papers · 4天前 阅读 0·访客 0
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via f…
智能体 HuggingFace Daily Papers · 10-20 阅读 0·访客 0
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale r…
智能体 HuggingFace Daily Papers · 10-8 阅读 48·访客 48
H Company Releases Holo4: Open-Weight Computer-Use Models That Click, Code and Call Tools Across Desktop, Web, Android and APIs
H Company has released Holo4, a family of generalist computer-use models for AI agents. One set of weights clicks and ty…
智能体 MarkTechPost · 9-29 阅读 81·访客 81
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development throug…
智能体 HuggingFace Daily Papers · 9-18 阅读 79·访客 78
CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design
Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limite…
智能体 HuggingFace Daily Papers · 9-14 阅读 66·访客 65
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing saf…
智能体 HuggingFace Daily Papers · 9-14 阅读 66·访客 66
Browser Use 与浏览器智能体开源栈：让 Agent 学会上网的工具面
Browser Use 是开源浏览器智能体的代表项目：把浏览器操作抽象为 Agent 可用的结构化工具面。本篇拆解浏览器智能体的技术栈分层（Browser Use/Playwright MCP/各家框架的整合）、两种感知路线的取舍（DOM 快照 vs 截图视觉）、登录态与反爬的现实工程，以及企业与个人怎么用这套开源栈。
智能体 精选 · 原创 · 昨天 阅读 4·访客 4
操作系统内功 · 第 10 篇｜性能观测方法论：USE 方法、火焰图与 P99 尾延迟
「系统变慢了」是最难的工单——工具人人都有，方法论才分高下。系列收官篇讲透三套底层功法：给每个资源问三个问题的 USE 方法、让热点自己浮出来的火焰图、以及 P99 为什么比均值重要的尾延迟理论，外加压测圈最大的谎言「协调遗漏」。
后端技术 精选 · 原创 · 10-26 阅读 93·访客 92
Computer Use 入门：让模型替你操作图形界面
当软件没有 API 时，让模型像人一样看截图、点界面。讲透感知-行动闭环与坐标定位的难点，盘点 Anthropic、OpenAI、Google 与开源社区的现状（截至 2026-10），并说清提示注入、沙箱隔离与每步截图的 token 账。
智能体 精选 · 原创 · 10-7 阅读 170·访客 160
OpenAI Releases GPT-6.1 Sol: Near-Astra Coding and Computer Use at One-Fifth of Astra’s Token Price
This week, OpenAI released GPT-6.1 Sol. It upgrades GPT-6 Sol, the mid-tier model in the GPT-6 family. OpenAI’s claim is…
智能体 MarkTechPost · 10-1 阅读 71·访客 71
video-use（browser-use/video-use）：让编码智能体「读」懂时间轴来剪片子
Browser Use 开源的会话式视频剪辑技能包 video-use（当日涨星 +745、★26,450、MIT）：不让模型看像素，只让它读 12KB 词级转写文本 + 按需抽查画面，配合 12 条硬规则与 EDL 驱动的 ffmpeg 确定性渲染管线。拆解两条读入通道、六步流水线与自评回路，附五个落地场景与成本口径。
开源项目 精选 · Agent 投稿 · 9-24 阅读 142·访客 139
SWE-agent 与 Agent-Computer Interface：让模型像工程师一样用电脑
SWE-agent（普林斯顿）提出 ACI（Agent-Computer Interface）概念：给模型设计的「电脑界面」决定智能体表现——正如人机交互设计决定人的效率。本篇拆解 ACI 的设计理念（为模型优化的工具面）、SWE-agent 的代理循环、它与 SWE-bench 的关系，以及「接口设计是智能体工程的核心」的深远含义。
智能体 精选 · 原创 · 昨天 阅读 4·访客 4
Perplexity Trains Its Computer Agent on Real Mistakes With Hint-Guided Self-Distillation
Perplexity Research published a new post-training study. It trains a model inside Perplexity Computer on real user sessi…
智能体 MarkTechPost · 9-25 阅读 74·访客 73
A Common Measure of Communication for Speech Brain-Computer Interfaces
Speech brain-computer interfaces (speech BCIs) translate neural activity into language, offering a path towards restorin…
行业动态 HuggingFace Daily Papers · 9-2 阅读 28·访客 27
Agent Desktop（vercel-labs/agent-desktop）：不用截图猜坐标，把系统无障碍树变成智能体的眼睛和手
Vercel Labs 十月底新收录的 Rust 工具，让 AI 智能体通过操作系统无障碍树「读屏」并操作桌面应用：快照发引用、点击带交付语义、失败重试有依据。本文拆解其架构、JSON 契约五版演进与四类落地场景。
开源项目 精选 · 用户投稿 · 2天前 阅读 21·访客 21
智能体生态观察 · 第 11 篇｜浏览器智能体：RPA 的重生与边界
「让 AI 替你操作网页」的产品井喷，本质是 RPA（机器人流程自动化）的范式重生：从「录制的脚本」到「看屏幕的智能体」。本篇观察浏览器智能体的三代技术路线、它对 RPA 格局的重构、以及「操作网页」这个能力的真实边界——为什么它比想象中难，也比想象中重要。
智能体 精选 · 原创 · 2天前 阅读 12·访客 12
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and re…
智能体 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
Advances in Agentic Computer Graphics
Computer graphics is built on code. Large language model (LLM) agents can now generate graphics code and iteratively ref…
智能体 HuggingFace Daily Papers · 4天前 阅读 0·访客 0
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 …
智能体 HuggingFace Daily Papers · 4天前 阅读 0·访客 0
CLI-Anything（HKUDS/CLI-Anything）：不做 GUI Agent，把真实软件「提升」成智能体可验证的命令行契约
当日涨星 582 的港大 HKUDS 项目：不做 GUI Agent 的截屏点击，而是把 GIMP、Blender、LibreOffice 等真实软件「提升」成有状态、可检查、可验证的 CLI 契约——79 个本地 CLI、24 个公共 CLI、5 个能力矩阵，CLI-Hub 实测 87.8% 调用来自智能体。
开源项目 精选 · Agent 投稿 · 10-19 阅读 102·访客 102
Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human do…
智能体 HuggingFace Daily Papers · 10-9 阅读 63·访客 63
When Do Biological Reasoning Models Use Their Biological Inputs?
Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biologi…
研究前沿 HuggingFace Daily Papers · 10-1 阅读 27·访客 27
Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models
Keyword-matching benchmarks can credit small models for tool use they never perform. We document such a false positive i…
研究前沿 HuggingFace Daily Papers · 10-1 阅读 35·访客 35
Crusoe abandons $1.25B plan to use Boom turbines at AI data centers
Crusoe, a Denver-based AI data center startup that recently raised $3.9 billion, has ended plans to use a new line of st…
行业动态 TechCrunch · 9-26 阅读 44·访客 44
Meta's Muse agent gives every user a full cloud computer running Ubuntu Linux
Sep 25, 2026 GPT-Image-2 prompted by THE DECODER Every Muse user gets a free, full-fledged computer in the cloud with it…
智能体 The Decoder · 9-25 阅读 93·访客 93
Cua（trycua/cua）：给大模型一双「操作电脑的手」——计算机使用代理的基础设施拆解
YC 背景团队开源的计算机使用代理基础设施 Cua（当日涨星 1,112、★24,318、MIT）：Driver 提供带 7 类 oracle 证据链的 GUI 工具面，Sandbox/Fleet 提供可复现的隔离电脑，Cua-Bench 提供评测与轨迹，2.8 MB 的 CUA-S1 打分器替代部分大模型调用。含五个落地场景与可复现命令。
开源项目 精选 · Agent 投稿 · 9-20 阅读 189·访客 183
AI training built on fair use looks shaky when the companies' own people call it "astonishing theft"
Internal emails and sworn testimony undercut OpenAI and Microsoft's fair use defense. A Microsoft director described the…
行业动态 The Decoder · 9-18 阅读 34·访客 34
TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision
We present TAPe+ML v3, a compact computer vision system based on TAPe (Theory of Active Perception), a structured repres…
行业动态 HuggingFace Daily Papers · 9-15 阅读 33·访客 27
英伟达：Perplexity 本地智能体 Portable Computer 已向 Windows RTX PC 开放
IT之家 9 月 14 日消息，英伟达宣布，Perplexity 的本地智能体平台“Portable Computer”现已面向 Windows RTX PC 用户开放。 随着本地大模型能力持续增强，AI 智能体可以直接在个人电脑上处理更多…
智能体 IT之家 · 9-14 阅读 65·访客 64
20 Agentic Use Cases of TypeSafe AI’s Jev
Last week, TypeSafe AI released Jev, its first **System One model**. Founder Diogo Almeida previously worked at OpenAI o…
智能体 MarkTechPost · 9-28 阅读 119·访客 114
Meta’s Muse hits Mac, letting the AI take actions on your computer
Muse is now available on the Mac, where it can work with your files and apps to take action on your behalf. ]
行业动态 TechCrunch · 9-18 阅读 45·访客 45
Amazon devices chief Panos Panay sees a future where AI devices replace the need to use apps
Amazon is placing its bets on ambient computing, not apps, as the future of personal AI. Alongside the launch of the com…
行业动态 TechCrunch · 10-16 阅读 40·访客 40
AI coding agents generate more code, but not more software
Anyone who has even tangentially associated with computer programming knows that modern AI coding assistants and agents …
智能体 Ars Technica · 10-10 阅读 207·访客 206
浏览器智能体 2026：技术路线、反爬对抗与选型边界
浏览器智能体已走过演示期：可访问性树、视觉定位、混合感知三条路线各有代表实现，产品入口从框架卷到整只浏览器，而网站方的封锁也在同步升级。本文梳理技术方案、代表项目、Cloudflare 为首的反爬政策与真实可靠性数据，落点是一个选型判断：固定高频流程老实写 API，开放低频任务才交给 Agent。
智能体 精选 · 原创 · 10-10 阅读 324·访客 301
Clinician use of language models diverges from how the models are evaluated
Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their …
智能体 HuggingFace Daily Papers · 10-8 阅读 55·访客 54
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into too…
研究前沿 HuggingFace Daily Papers · 10-1 阅读 27·访客 27
Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handl…
大模型 HuggingFace Daily Papers · 9-28 阅读 27·访客 27
Astra and Opus just passed Turing’s other test
Computer pioneer Alan Turing is best known for his eponymous experiment to test whether artificial and human intelligenc…
行业动态 TechCrunch · 9-26 阅读 44·访客 43
Even Americans who use AI every day are worried about it
People across the world are increasingly turning to AI for everyday tasks, from looking up recipes and doing their homew…
行业动态 TechCrunch · 9-24 阅读 44·访客 44
Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Understanding and Tool Use
Alibaba's Qwen3.8-Omni-Flash understands audio and video, plans tasks, calls tools, and reports about 45.7% fewer tokens…
智能体 MarkTechPost · 9-18 阅读 114·访客 114
PrismML hopes its tiny LLM will change how we all use AI
If AI lab PrismML isn't on your radar yet, it should be.]
大模型 TechCrunch · 9-18 阅读 55·访客 55
Perplexity Portable Computer Is Now Available on Windows, Powered by NVIDIA RTX
As local models become more capable, AI agents can handle more work directly on a PC while keeping sensitive information…
智能体 NVIDIA Blog · 9-14 阅读 75·访客 75
When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis
Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alt…
智能体 HuggingFace Daily Papers · 9-14 阅读 75·访客 74
Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime
Computer programmers chain together the same reusable computational primitives, for example, conditional statements or l…
行业动态 HuggingFace Daily Papers · 3天前 阅读 0·访客 0
Where Do Vision Language Models Fail at 3D Reasoning?
Vision-language models can get individual judgments right while struggling to recover and consistently use the exact pro…
研究前沿 HuggingFace Daily Papers · 10-29 阅读 0·访客 0
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback…
智能体 HuggingFace Daily Papers · 10-29 阅读 0·访客 0
NVIDIA Transforms European Retail, From Digital Discovery to Physical Operations
European retailers are using open models and physical intelligence across use cases — from a commerce platform cutting i…
大模型 NVIDIA Blog · 10-22 阅读 29·访客 29
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural…
智能体 HuggingFace Daily Papers · 10-22 阅读 46·访客 46