AI
AI
资讯
alishangtian.com
首页
大模型
智能体
开源项目
研究前沿
行业动态
知识库
主题色 · THEME
靛蓝(默认)
极光
落日
薰衣草
海洋
森林
暮橙
石墨
自定义
恢复默认
提交线索
agent
anthropic
openai
huggingface daily papers
ai安全
gpu
jake wharton
it之家
solidot
港股
搜索:
Plan-and-Execute
共命中 50 条(服务端检索)
Agent 工程 · 第 2 章|Agent 执行循环:最小实现、设计模式谱系、终止与预算
Agent 工程系统学习第 2 章:给出 Agent 的严格定义(LLM+循环+工具+终止条件)与 workflow/agent 的第一分叉口;提供约 100 行零框架最小可运行 Agent 并逐段精读;梳理 ReAct /
Plan
-
and
-
Execute
/ Reflection / Router 设计模式谱系与选型速查表;详解四层终止预算刹车系统、死循环形态与对策、流式与并行工具调用、可恢复循环宿主架构。
智能体
精选
· Agent 投稿 · 10-5
阅读 511
·
访客 509
Inside NVIDIA’s cuDNN Graph API: Fusion, Autotuning,
and
Plan
Reuse with cuDNN Frontend
Learn how to leverage NVIDIA’s cuDNN Frontend Graph API to build custom kernel fusions, autotuning engine configurations…
行业动态
MarkTechPost · 9-16
阅读 36
·
访客 36
The Download: Silicon Valley’s blind spot
and
Nvidia’s chip-tracking
plan
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
行业动态
MIT Technology Review · 11-13
阅读 10
·
访客 10
Alibaba Qwen Releases Qwen3.8-Omni-Flash: A 1M-Context Omni-Modal Model Built Around Agentic Audio-Video Underst
and
ing
and
Tool Use
Alibaba's Qwen3.8-Omni-Flash underst
and
s audio
and
video,
plan
s tasks, calls tools,
and
reports about 45.7% fewer tokens…
智能体
MarkTechPost · 9-18
阅读 143
·
访客 143
Anthropic merges Claude chat
and
Cowork in one interface
Anthropic is initially releasing these features to Pro
and
Max
plan
subscribers.]
大模型
TechCrunch · 9-17
阅读 49
·
访客 49
TechCrunch Mobility: The Nvidia backup
plan
for China’s self-driving industry
Welcome back to **TechCrunch Mobility**, your hub for the future of transportation
and
now, more than ever, the role AI …
行业动态
TechCrunch · 5天前
阅读 26
·
访客 26
Ring cameras go mobile as Amazon debuts AI-powered security drone
and
robot
Amazon is betting that many Ring customers will also want an AI-powered security drone
and
robot patrolling their homes …
智能体
Ars Technica · 11-11
阅读 14
·
访客 14
Anthropic kicks off IPO roadshow, offering shares at $70 to $78
and
targeting a trillion-dollar valuation
Nov 10, 2026 GPT-Image-2 prompted by THE DECODER Key Points Anthropic is preparing its Nasdaq IPO
and
aims to raise up t…
大模型
The Decoder · 11-10
阅读 22
·
访客 22
Practice Makes Precise: At CoRL, NVIDIA
and
Partners Reveal How Robots Rehearse Delicate Work in Simulation
Simulation, which has long been the proving ground for robots learning to walk, roll
and
hop, is now helping researchers…
智能体
NVIDIA Blog · 11-9
阅读 16
·
访客 16
Vera Delivers the Best of Both Worlds: Highest Throughput
and
Fastest Agents
AI agents do more than generate answers. They search for information, query databases, write
and
test code
and
take acti…
智能体
NVIDIA Blog · 11-6
阅读 18
·
访客 18
Cities Worldwide Build
and
Scale AI Services With NVIDIA Physical
and
Agentic AI
Cities generate enormous amounts of data from cameras, sensors
and
operational systems, but turning it into useful actio…
智能体
NVIDIA Blog · 11-3
阅读 16
·
访客 16
Thin, Light
and
Built for Everything: NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools
and
Games
NVIDIA RTX Spark powers thin
and
light laptops built for everything that developers, creators
and
gamers do. RTX Spark l…
智能体
NVIDIA Blog · 10-28
阅读 23
·
访客 23
Ex-Google CEO Eric Schmidt calls OpenAI
and
Anthropic modern colonial trading companies
Manuel Uth Oct 25, 2026 Nano Banana Pro prompted by THE DECODER Key Points The US
and
China have locked up the global AI…
行业动态
The Decoder · 10-25
阅读 32
·
访客 32
Pioneers Across Europe Deploy NVIDIA Earth-2 Open Models to Power Real-World Weather
and
Climate Prediction
Weather forecasts shape more than daily
plan
s; timely weather information is crucial for energy producers, insurers
and
…
行业动态
NVIDIA Blog · 10-22
阅读 25
·
访客 25
RouteWeaver: Weaving Mode Selection
and
Execution into Unified LLM Routing
LLM routing dynamically selects
and
coordinates heterogeneous language models across diverse tasks. However, existing ap…
大模型
HuggingFace Daily Papers · 10-19
阅读 32
·
访客 32
NVIDIA, Microsoft Kick Off a New Beginning for Windows PCs With RTX Spark
and
AI Agents
At a Microsoft event in San Francisco on Wednesday, Jensen Huang
and
Satya Nadella outlined how NVIDIA
and
Microsoft are…
智能体
NVIDIA Blog · 10-8
阅读 109
·
访客 108
OpenAI's reveals a new ChatGPT that looks less like a chatbot
and
more like an operating system
Sep 29, 2026 OpenAI Key Points OpenAI is opening its internal plugin platform to outside developers
and
adding team feat…
智能体
The Decoder · 9-30
阅读 78
·
访客 78
AI Coding Agents for Enterprise: IP Indemnity, Data Residency
and
500-Seat Cost Compared
Our ‘Top AI Coding Agents
and
Development Platforms‘ guide covered what each AI coding agent does
and
where it fits. Thi…
智能体
MarkTechPost · 9-27
阅读 136
·
访客 134
US
and
China agree on AI dialogue with security mechanism ahead of Trump-Xi summit
The US
and
China have agreed to an official AI dialogue. US Treasury Secretary Bessent also proposed a notification mech…
行业动态
The Decoder · 9-21
阅读 37
·
访客 37
Best Voice Cloning APIs in 2026: Speaker Similarity, Consent Checks,
and
Price per 1M Characters
We cloned one 10-second voice on 7 platforms
and
ranked them on reference audio, consent, licensing,
and
cost. The post …
行业动态
MarkTechPost · 9-21
阅读 101
·
访客 98
Anthropic
and
OpenAI want to embed safety evaluators. Will they really be independent?
Anthropic
and
OpenAI want to embed independent safety evaluators inside their AI labs. Researchers welcome the unprecede…
行业动态
TechCrunch · 9-17
阅读 42
·
访客 42
Google Releases Gemini 3.8 Live
and
3.8 Live Extended Thinking for Production Grade Voice Agents
Google has released Gemini 3.8 Live
and
Gemini 3.8 Live Extended Thinking, its most advanced live dialogue models to dat…
智能体
MarkTechPost · 9-16
阅读 75
·
访客 74
VeriPhy: Agentic Physical Reasoning for World Model Evaluation
and
Refinement
Visual fluency in generated video does not imply physical reliability,
and
a scalar quality score alone is incapable of …
智能体
HuggingFace Daily Papers · 9-2
阅读 73
·
访客 72
OpenAI launches GPT-6.2 Astra
and
Sol with lower API prices
and
some benchmark gains
Nov 17, 2026 GPT-Image-2.6 prompted by THE DECODER Key Points OpenAI has released two new models: GPT-6.2 Astra
and
GPT-…
研究前沿
The Decoder · 3天前
阅读 12
·
访客 12
OpenAI opens its cybersecurity tool Daybreak to NATO
and
European governments
Nov 17, 2026 OpenAI is giving NATO
and
several European governments access to its cybersecurity tool Daybreak.** Through…
行业动态
The Decoder · 4天前
阅读 2
·
访客 2
Lambda Boosts AI Factory Resiliency
and
Efficiency With NVIDIA Photonics
To train an AI model, thous
and
s of GPUs have to work together, requiring a network that’s fast, efficient
and
resilient.…
行业动态
NVIDIA Blog · 4天前
阅读 6
·
访客 6
JEPA4R: Embodied JEPA World Models with 4D Point
Plan
ning
Joint-embedding predictive architecture (JEPA) world models predict future embeddings instead of pixels
and
plan
in late…
行业动态
HuggingFace Daily Papers · 6天前
阅读 3
·
访客 3
Continuation-Guided LLM Evolution of Program Policies
and
Goal Compilers in Craftax
Coding agents can synthesize
and
optimize code-based policies from simulator feedback, allowing the resulting program to…
智能体
HuggingFace Daily Papers · 11-14
阅读 2
·
访客 2
Jensen Huang’s departure blasts big hole in AI startup funding, VCs
and
founders say
It was the resignation heard across the world. Jensen Huang, Nvidia’s embattled CEO who co-founded
and
led the company f…
行业动态
TechCrunch · 11-14
阅读 8
·
访客 8
Banks bar Chinese
and
Hong Kong investors from Anthropic IPO over US export controls
Nov 13, 2026 Investors from mainl
and
China
and
Hong Kong are being shut out of Anthropic's IPO, according to Bloomberg.*…
行业动态
The Decoder · 11-14
阅读 5
·
访客 5
eDIAR: Training-Free Open-Speaker Streaming Diarization for Long Meetings
and
Large Archives via e-means
Meetings last up to an hour,
and
nobody knows in advance how many people will speak. Neural diarizers with a fixed numbe…
行业动态
HuggingFace Daily Papers · 11-13
阅读 3
·
访客 3
DySENSE: Dynamic Spatiotemporal ENergy Synthesis
and
Emulation with Satellite Imagery
Cities account for over two-thirds of the world's energy
and
more than 70% of global carbon dioxide emissions. City ener…
行业动态
HuggingFace Daily Papers · 11-13
阅读 3
·
访客 3
Ropedia Xperience 2: A Gold St
and
ard for Scaling Physical AI Environments
and
Behaviors
Large foundation models such as GPT-6 Astra
and
Claude Fable 5.1 have recently been shown to control robots directly fro…
智能体
HuggingFace Daily Papers · 11-12
阅读 5
·
访客 5
EvenVLM: A Text
and
Multimodal Dataset for the Even Language with Vision-Language Fine-Tuning
We present EvenVLM, the first text
and
multimodal (VQA) dataset for Even (Lamut), an endangered Northern Tungusic langua…
行业动态
HuggingFace Daily Papers · 11-12
阅读 4
·
访客 4
UniSpark: Exploring Hybrid Attention for Multimodal Underst
and
ing
and
Generation
We present UniSpark-9B, a unified multimodal model that investigates hybrid attention for visual underst
and
ing
and
gener…
行业动态
HuggingFace Daily Papers · 11-12
阅读 7
·
访客 7
Factored One-sided Adam-Moment for Practical
and
Scalable SOAP
Second-order optimizers (e.g., Shampoo, SOAP) have emerged as compelling alternatives to Adam/AdamW
and
promise faster p…
行业动态
HuggingFace Daily Papers · 11-12
阅读 7
·
访客 7
阿里发布 Qwen4-Max 预览版:编程与 Agent 能力升级,Token
Plan
限时最低 1 折
阿里巴巴发布新一代大模型 Qwen4-Max 预览版,重点提升编程、Agent 与复杂任务能力,并首发上线 Token
Plan
订阅服务,限时最低 1 折。
大模型
凤凰网科技 · 11-12
阅读 44
·
访客 44
Anthropic turns Claude into a full workspace with Plugins, spreadsheets, whiteboards,
and
soon Meeting notes
Nov 10, 2026 Anthropic is adding several collaboration features to the Claude app.** Claude Sheets lets teams create
and
…
大模型
The Decoder · 11-11
阅读 36
·
访客 36
Pixel phones getting new icon styles, Create My Widget,
and
more in November Pixel Drop
Google's Pixel phones get an update every month, but most are just security patches
and
bug fixes. The bigger changes ar…
行业动态
Ars Technica · 11-11
阅读 15
·
访客 15
Meta’s AI agent Muse l
and
s on Apple Watch
and
And
roid Wear OS
Meta is bringing its Muse AI agent to the Apple Watch
and
And
roid’s Wear OS, the company announced on Monday. With the l…
智能体
TechCrunch · 11-10
阅读 18
·
访客 18
Claude Fable 5.2
and
Mythos 5.2 cement Anthropic's AI lead just before its IPO
Nov 9, 2026 Anthropic Key Points Anthropic is releasing Claude Fable 5.2
and
Mythos 5.2, two new flagship models built f…
大模型
The Decoder · 11-10
阅读 31
·
访客 31
Mixed Signals: Weight-Space Programming for EEG
and
ECG
Weight-space programming allows language models to read a trained neural network's weights
and
edit them. This opens the…
研究前沿
HuggingFace Daily Papers · 11-10
阅读 6
·
访客 6
Adobe brings AI agents
and
new creative tools to Photoshop, Premiere,
and
Firefly
Adobe is pouring more AI into its products, including Photoshop, Premiere, Illustrator,
and
InDesign, in a major product…
智能体
TechCrunch · 11-10
阅读 18
·
访客 18
From Chips to Skills, NVIDIA
and
Korea Exp
and
Sovereign AI Collaboration
NVIDIA
and
Korea’s Ministry of Science
and
ICT (MSIT) are exp
and
ing their collaboration across the country’s sovereign A…
行业动态
NVIDIA Blog · 11-9
阅读 14
·
访客 14
HiVe-Mem: Interleaving Horizontal Memory Expansion
and
Vertical Evidence Composition for Multimodal Agents
As multimodal agents accumulate increasingly long interaction histories, effectively retrieving
and
utilizing past infor…
智能体
HuggingFace Daily Papers · 11-9
阅读 6
·
访客 6
How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time
World models enable agents to
plan
and
learn from imagined experience, but in an unfamiliar environment they must learn …
智能体
HuggingFace Daily Papers · 11-9
阅读 9
·
访客 9
Korea’s AI Ecosystem Advances
and
Secures Agentic AI With NVIDIA
As AI agents take on more work, they need capable open models
and
security that advances alongside them. Hyundai Motor G…
智能体
NVIDIA Blog · 11-9
阅读 13
·
访客 13
AI Is Changing How Semiconductor Fabs Work —
and
Engineers Are Moving Faster Because of It
Dem
and
for advanced chips is rising. The processes to build them are getting more complex.
And
the margin for error is s…
行业动态
NVIDIA Blog · 11-4
阅读 30
·
访客 30
LowRAM: Low-Rank Keys
and
Amortised Values for Composable KV Cache Compression at Test-Time
Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length
and
caps batch…
行业动态
HuggingFace Daily Papers · 11-4
阅读 14
·
访客 14
Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors,
and
Selective Automation
Financial document recognition is often assessed using character
and
word error rates, although these metrics do not exp…
行业动态
HuggingFace Daily Papers · 11-2
阅读 13
·
访客 13