正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Meet Embodied Web Agents that bridge physical-digital realms. Imagine embodied agents that can search for online recipes, shop for ingredients and cook for you. Embodied web agents search internet information for implementing real-world embodied tasks. All data, codes and web environments are available at Paper link:

Yining Hong

4,665 subscribers

54,908 次观看 • 1 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

4 条评论

Sarthak Gupta 的头像

Sarthak Gupta1 年前

This paper looks awesome! Would love to know what you used to generate these outdoor environments

Yining Hong 的头像

Yining Hong1 年前

Hi, we use unreal google earth

J 的头像

J1 年前

非常好玩。^=^

Yining Hong 的头像

Yining Hong1 年前

Thank you:)

相关视频

You can now officially use Exa web search inside Grok Build! Exa is the fastest and most accurate web search, built for agents.

You can now officially use Exa web search inside Grok Build! Exa is the fastest and most accurate web search, built for agents.

Exa

473,609 次观看 • 2 个月前

Today we're releasing Mk1.5: a new intelligence layer for embodied agents. It flies drones, controls quadrupeds, powers smart glasses, tracks objects, searches the web, reasons visually, and dispatches its own sub-agents. One model, no platform-specific retraining. 🧵

Today we're releasing Mk1.5: a new intelligence layer for embodied agents. It flies drones, controls quadrupeds, powers smart glasses, tracks objects, searches the web, reasons visually, and dispatches its own sub-agents. One model, no platform-specific retraining. 🧵

Perceptron AI

142,650 次观看 • 7 天前

Introducing Web Search Agents: expert level web search that self-learns your domain to deliver perfect web context, while burning less tokens. Generic web search tools start from scratch every time they run. Web Search Agents compound their expertise to adapt web search and crawling to your use case — finding the exact data you need, more efficiently. Learn more below in our blog:

Introducing Web Search Agents: expert level web search that self-learns your domain to deliver perfect web context, while burning less tokens. Generic web search tools start from scratch every time they run. Web Search Agents compound their expertise to adapt web search and crawling to your use case — finding the exact data you need, more efficiently. Learn more below in our blog:

Nimble

363,367 次观看 • 2 个月前

Nimble is now an OpenAI plugin for ChatGPT and Codex, giving OpenAI models deeper context from the web. With Nimble, ChatGPT and Codex can: - Discover more complete web context by combining web search with computer use to navigate and paginate websites, capturing data that doesn’t show up in search results - Improve web search efficiency with self-learning agents that optimize web retrieval methodology after every run - Govern web retrieval with source controls, confidence scores, and evidence for every data point Available now in the Plugins tab. Learn more here:

Nimble is now an OpenAI plugin for ChatGPT and Codex, giving OpenAI models deeper context from the web. With Nimble, ChatGPT and Codex can: - Discover more complete web context by combining web search with computer use to navigate and paginate websites, capturing data that doesn’t show up in search results - Improve web search efficiency with self-learning agents that optimize web retrieval methodology after every run - Govern web retrieval with source controls, confidence scores, and evidence for every data point Available now in the Plugins tab. Learn more here:

Nimble

99,231 次观看 • 9 天前

Information agents in Search are now available globally for Google AI Ultra subscribers. They can keep you updated on topics, tasks or projects you care about — and send you intelligent, comprehensive updates with links across the web so you can take action. #GoogleIO

Information agents in Search are now available globally for Google AI Ultra subscribers. They can keep you updated on topics, tasks or projects you care about — and send you intelligent, comprehensive updates with links across the web so you can take action. #GoogleIO

Google

99,761 次观看 • 3 个月前

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Firecrawl

123,983 次观看 • 5 个月前

Introducing the new Firecrawl CLI 🔥 The toolkit for agents to scrape, search, and browse the web. - Scrape clean data from any page - Search the web and get full results back - Spin up cloud browsers for interactive flows npx -y firecrawl-cli@latest init --all --browser

Introducing the new Firecrawl CLI 🔥 The toolkit for agents to scrape, search, and browse the web. - Scrape clean data from any page - Search the web and get full results back - Spin up cloud browsers for interactive flows npx -y firecrawl-cli@latest init --all --browser

Firecrawl

357,103 次观看 • 6 个月前

Introducing Ego2Web from Google DeepMind and UNC Chapel Hill, accepted to #CVPR2026. AI agents can browse the web. But can they act based on what you see? Existing benchmarks focus only on web interaction while ignoring the real world. Ego2Web bridges egocentric video perception and web execution, enabling agents that can see through first-person video, understand real-world context, and take actions on the web grounded in the egocentric video. This opens a path toward AI assistants that operate seamlessly across physical and digital environments. We hope Ego2Web serves as an important step for building more capable, perception-driven agents. 🧵👇

Introducing Ego2Web from Google DeepMind and UNC Chapel Hill, accepted to #CVPR2026. AI agents can browse the web. But can they act based on what you see? Existing benchmarks focus only on web interaction while ignoring the real world. Ego2Web bridges egocentric video perception and web execution, enabling agents that can see through first-person video, understand real-world context, and take actions on the web grounded in the egocentric video. This opens a path toward AI assistants that operate seamlessly across physical and digital environments. We hope Ego2Web serves as an important step for building more capable, perception-driven agents. 🧵👇

Shoubin Yu

45,940 次观看 • 6 个月前

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

🚨🚨Can agents earn money, run a business, or even self-organize a society in the physical social world? 🤖🤖 Can agents learn continually to survive and thrive in embodied environments, like how human babies grow? 👶 Super excited to introduce SimWorld, an open-ended simulator of LLM agents in infinite, realistic embodied worlds. SimWorld features 3 key designs: 1⃣Open-ended realistic world simulation - built on Unreal Engine 5, with accurate physical social dynamics - 100+ built-in environments (city, island, wilderness ...) - language-controllable procedural generation - text-to-3D asset generation 2⃣Native interface for LLM/VLM agents - Gym-like agent-environment interaction APIs - plug in any LLMs/VLMs (GPTs, Gemini, Qwen ...) - rich multi-modal perception - open-vocabulary natural-language action outputs 3⃣Diverse physical and social reasoning scenarios - long-horizon embodied reasoning - multi-agent collaboration / competition - easily customizable for any reasoning tasks SimWorld is fully open-sourced, with a hope to become a foundational infrastructure for real-world agent research across disciplines: robotics, economy, public health, education, etc. Project website + more details in the thread👇 ...1/

Lianhui Qin

65,267 次观看 • 10 个月前

You built an agent and you're still doing research by hand? Give it web search made for agents — CLI, REST, MCP.

You built an agent and you're still doing research by hand? Give it web search made for agents — CLI, REST, MCP.

Keenable AI

55,809 次观看 • 2 个月前

Introducing Boba Agents, now live with free credits. We built OpenCode for trading - no APIs needed, access real market data for millions of tokens and RWAs. Trade smarter with semantic memory, automations, specialized agents, tool calls, and web search. Built for all models like Kimi 2.5, no setup required.

Introducing Boba Agents, now live with free credits. We built OpenCode for trading - no APIs needed, access real market data for millions of tokens and RWAs. Trade smarter with semantic memory, automations, specialized agents, tool calls, and web search. Built for all models like Kimi 2.5, no setup required.

Boba

16,227 次观看 • 6 个月前

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their context window. Parallel’s Search API is built from the ground up for AI agents, resulting in higher accuracy, lower costs, and lower latency for end-to-end agentic workflows.

Today, we’re launching the Parallel Search API, the most accurate web search for AI agents, built using our proprietary web index and retrieval infrastructure. Traditional search ranks URLs for humans to click. AI search needs something different: the right tokens in their context window. Parallel’s Search API is built from the ground up for AI agents, resulting in higher accuracy, lower costs, and lower latency for end-to-end agentic workflows.

Parallel Web Systems

670,356 次观看 • 11 个月前

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

🚨 THIS IS ACTUALLY INSANE Your AI agent can have access to the web. But if it can't reliably read what’s actually on the page, that access is almost useless. We looked at Firecrawl as the web layer for AI agents and the numbers are hard to ignore. The setup is simple: Give it a URL, search query, or website. Firecrawl handles the ugly part — crawling, scraping, rendering, extracting, and turning web content into something an AI model can actually use. The headline numbers: → 173,000+ GitHub stars → Search, scrape and interact with the web at scale → Supports web pages, PDFs, DOCX and other content → Structured data extraction for AI workflows → MCP support for connecting it directly to AI agents The workflow looks like this: Search → Scrape → Crawl → Extract → Feed the agent Three things stand out: 1. Scraping becomes an infrastructure layer Instead of maintaining your own pile of HTTP clients, parsers, browser automation and retry logic, you can treat web access as an API. 2. Agents get more than raw HTML The goal isn't just downloading a webpage. It's turning messy web content into clean context that an LLM can reason over. 3. The same layer works across different agent workflows Research agents. RAG pipelines. AI search. Competitive intelligence. Web-data extraction. The interesting shift: AI agents don't just need better models. They need better access to the information those models are supposed to reason about. Firecrawl is building that layer. Save this repo.

Vikas gupta

18,053 次观看 • 27 天前

Introducing the Firecrawl Skill + CLI for Agents 🔥 Agents like Claude Code, Codex, and OpenCode need live quality context from the web. The CLI pulls web content to local files with bash-powered search for the highest token efficiency. $ npx skills add firecrawl/cli

Introducing the Firecrawl Skill + CLI for Agents 🔥 Agents like Claude Code, Codex, and OpenCode need live quality context from the web. The CLI pulls web content to local files with bash-powered search for the highest token efficiency. $ npx skills add firecrawl/cli

Firecrawl

87,256 次观看 • 8 个月前

TinyFish has made web Search and Fetch features FREE for all developers and AI agents, with generous rate limits! > Search: Low-latency search responses for agentic use > Fetch: Real browser render, clean markdown, or JSON outputs > Works with Claude Code, OpenClaw, Cursor, Codex, n8n, Dify, and more

TinyFish has made web Search and Fetch features FREE for all developers and AI agents, with generous rate limits! > Search: Low-latency search responses for agentic use > Fetch: Real browser render, clean markdown, or JSON outputs > Works with Claude Code, OpenClaw, Cursor, Codex, n8n, Dify, and more

🚨 AI News | TestingCatalog

32,989 次观看 • 5 个月前

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

Tencent Hy

34,317 次观看 • 5 个月前