Loading video...

Video Failed to Load

Go Home

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's profile picture

Yining Hong

4,414 subscribers

54,264 views • 1 year ago •via X (Twitter)

Science & TechnologyEducationArts
LIVE

Anya Rossi• Live Now

Private livecam show

4 Comments

Sarthak Gupta's profile picture
Sarthak Gupta1 year ago

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

Yining Hong's profile picture
Yining Hong1 year ago

Hi, we use unreal google earth

J's profile picture
J1 year ago

非常好玩。^=^

Yining Hong's profile picture
Yining Hong1 year ago

Thank you:)

Related Videos

Embodied Web Agents Bridging Physical-Digital Realms for Integrated Agent Intelligence
1:06

Embodied Web Agents Bridging Physical-Digital Realms for Integrated Agent Intelligence

AK

57,187 views • 1 year ago

Scaling embodied AI starts with automating the environments. Introducing SimWorld Studio: a self-evolving factory for endless interactive 3D environments where agents act, fail, and learn. With coding-agent + embodied-agent co-evolution, navigation success improves from 50% → 90%. 1/
1:36

Scaling embodied AI starts with automating the environments. Introducing SimWorld Studio: a self-evolving factory for endless interactive 3D environments where agents act, fail, and learn. With coding-agent + embodied-agent co-evolution, navigation success improves from 50% → 90%. 1/

Lianhui Qin

59,049 views • 1 month ago

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
1:03

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

98,023 views • 29 days ago

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.
0:25

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

123,163 views • 3 months ago

🔥 Introducing Firecrawl /search. Firecrawl just launched an insane feature to search and crawl in one shot. You heard that right! One API call to search the web and scrape any data you need for your AI agents. I took it for a spin in n8n:
7:57

🔥 Introducing Firecrawl /search. Firecrawl just launched an insane feature to search and crawl in one shot. You heard that right! One API call to search the web and scrape any data you need for your AI agents. I took it for a spin in n8n:

elvis

42,656 views • 1 year ago

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
0:43

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

356,015 views • 4 months ago

🚨🚨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/
1:10

🚨🚨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

64,864 views • 7 months ago

❌ Do NOT use OpenAI for real-time web search - they index the web for fast yet inaccurate replies. 🚀 We’re releasing Browser Use Search API today. It crawls sites and fetches real-time data by interacting with any website. Built because you asked for it. We have already enterprises on board who use this API for web search. If you build general or vertical agents you can use this to enable browser interaction. See how it performs vs ChatGPT 🫣
0:21

❌ Do NOT use OpenAI for real-time web search - they index the web for fast yet inaccurate replies. 🚀 We’re releasing Browser Use Search API today. It crawls sites and fetches real-time data by interacting with any website. Built because you asked for it. We have already enterprises on board who use this API for web search. If you build general or vertical agents you can use this to enable browser interaction. See how it performs vs ChatGPT 🫣

Browser Use

63,567 views • 11 months ago

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.
2:29

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

15,694 views • 4 months ago

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.
1:20

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

669,541 views • 8 months ago

Agents can now search and scrape the web with a single API call. Firecrawl's /search endpoint returns complete LLM-ready content for every search result. HTML, Markdown, or JSON. Works via API, MCP for Cursor, Zapier and n8n.
0:45

Agents can now search and scrape the web with a single API call. Firecrawl's /search endpoint returns complete LLM-ready content for every search result. HTML, Markdown, or JSON. Works via API, MCP for Cursor, Zapier and n8n.

Lior Alexander

14,812 views • 1 year ago

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
0:24

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 views • 5 months ago

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:
0:54

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 views • 3 months ago

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
0:32

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 views • 2 months ago

🚨 NEURA unveils “NEURA Gym” — a physical AI training ground for robots. Hundreds of humanoids and robotic systems will learn real-world skills side by side, collecting data that feeds into the Neuraverse — a global infrastructure for embodied AI.
0:23

🚨 NEURA unveils “NEURA Gym” — a physical AI training ground for robots. Hundreds of humanoids and robotic systems will learn real-world skills side by side, collecting data that feeds into the Neuraverse — a global infrastructure for embodied AI.

Humanoids daily

25,469 views • 9 months ago

5 huge AI agents, MCP, and LLM updates today: 1. China just dropped an opensource Deep Research multi-agent framework with MCP support. It connects AI Agents with specialized tools for tasks like web search, crawling, and Python code execution. 100% opensource.
1:16

5 huge AI agents, MCP, and LLM updates today: 1. China just dropped an opensource Deep Research multi-agent framework with MCP support. It connects AI Agents with specialized tools for tasks like web search, crawling, and Python code execution. 100% opensource.

Unwind AI

79,540 views • 1 year ago

The industry's first embodied AI IDE, Booster Studio, is officially live at Built exclusively for embodied AI, Booster Studio integrates code editing, high-precision simulation, real-robot debugging, and real-world deployment into a single platform. Experience a true one-stop journey from your first idea to final hardware deployment. With its high-fidelity simulation environment and comprehensive development stack, Booster Studio shatters the barrier between digital and physical, bringing embodied AI to life. #boosterrobotics #embodiedai
1:21

The industry's first embodied AI IDE, Booster Studio, is officially live at Built exclusively for embodied AI, Booster Studio integrates code editing, high-precision simulation, real-robot debugging, and real-world deployment into a single platform. Experience a true one-stop journey from your first idea to final hardware deployment. With its high-fidelity simulation environment and comprehensive development stack, Booster Studio shatters the barrier between digital and physical, bringing embodied AI to life. #boosterrobotics #embodiedai

Booster Robotics

591,822 views • 15 days ago

The web wasn't built for AI agents. So we built Firecrawl. - /search finds fresh, relevant sources from the web - /scrape turns any URL into clean context for AI - /interact automates clicks, pagination, and logins Join 1,000,000+ developers connecting intelligence to the web.
1:06

The web wasn't built for AI agents. So we built Firecrawl. - /search finds fresh, relevant sources from the web - /scrape turns any URL into clean context for AI - /interact automates clicks, pagination, and logins Join 1,000,000+ developers connecting intelligence to the web.

Firecrawl

4,711,662 views • 1 month ago

[NeurIPS D&B Oral] Embodied Agent Interface: Benchmarking LLMs for Embodied Agents A single line of code to evaluate your model! 🌟Standardize Goal Specifications: LTL 🌟Standardize Modules and Interfaces: 4 modules, 438 tasks, 1475 goals 🌟Standardize Fine-grained Metrics: 18 models, 42 metrics, 100+ page analysis Website: Dataset: Code: Docker: PyPI: Doc:
0:53

[NeurIPS D&B Oral] Embodied Agent Interface: Benchmarking LLMs for Embodied Agents A single line of code to evaluate your model! 🌟Standardize Goal Specifications: LTL 🌟Standardize Modules and Interfaces: 4 modules, 438 tasks, 1475 goals 🌟Standardize Fine-grained Metrics: 18 models, 42 metrics, 100+ page analysis Website: Dataset: Code: Docker: PyPI: Doc:

Manling Li

132,665 views • 1 year ago

Introducing /search - the simplest way for agents and devs to discover the web 👀 Our #1 most requested endpoint is finally here. Search the web AND scrape all results in an LLM-ready format with one API call. Now live on our API, MCP, and all integrations 🔥
1:34

Introducing /search - the simplest way for agents and devs to discover the web 👀 Our #1 most requested endpoint is finally here. Search the web AND scrape all results in an LLM-ready format with one API call. Now live on our API, MCP, and all integrations 🔥

Firecrawl

390,772 views • 1 year ago