Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

4. A search agent with multi-step trip planning and reasoning

chiefaioffice's profile picture

Chief AI Officer

35,165 subscribers

56,086 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

9 Yorum

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

TLDR: Google is ALL IN on AI agents AI agents are deployed across their whole product ecosystem. 8 wild demos from Google I/O today: 1. An email agent to continuously organise all receipts in your inbox into a spreadsheet

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

2. An email agent to return an order

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

3. An email agent to sort through multiple conversations, files to answer questions

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

5. A search agent with multi-step researching and reasoning to find a pilates class

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

6. A search agent with multi-step researching, reasoning & shopping to prepare a meal plan

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

7. A browser agent to work across multiple external websites to do tasks like updating addresses across dozens of websites

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

8. An AI teammate that lives inside Google workspace to do collaborative tasks

Chief AI Officer profil fotoğrafı
Chief AI Officer2 yıl önce

Interested in AI startups? Join 5000+ tracking venture rounds in AI and get access to my free funding database:

UserInterface profil fotoğrafı
UserInterface4 yıl önce

Show Us Your Style. We Want to See. Who is the best dressed in the city? Build your fashion profile. Tell a friend. #style #fashion

Benzer Videolar

6. A search agent with multi-step researching, reasoning & shopping to prepare a meal plan
0:41

6. A search agent with multi-step researching, reasoning & shopping to prepare a meal plan

Chief AI Officer

43,459 görüntüleme • 2 yıl önce

I built a Deepseek R1 RAG Reasoning Agent running locally on my computer. It's an Agentic RAG reasoning agent that can think, reason and fall back to web search if needed. 100% Opensource code with step-by-step tutorial.
1:50

I built a Deepseek R1 RAG Reasoning Agent running locally on my computer. It's an Agentic RAG reasoning agent that can think, reason and fall back to web search if needed. 100% Opensource code with step-by-step tutorial.

Shubham Saboo

124,490 görüntüleme • 1 yıl önce

Build Multi Agent Systems with Reasoning and Context Thanks to sonnet-4, we have level 4 autonomous multi-agent systems working. Learn how to add: -> Reasoning Tools (think -> analyze) -> Shared Agentic Context -> Agentic Memory Code below 👇
14:17

Build Multi Agent Systems with Reasoning and Context Thanks to sonnet-4, we have level 4 autonomous multi-agent systems working. Learn how to add: -> Reasoning Tools (think -> analyze) -> Shared Agentic Context -> Agentic Memory Code below 👇

Ashpreet Bedi

38,576 görüntüleme • 1 yıl önce

LLM agents have demonstrated promise in their ability to automate computer tasks, but face challenges with multi-step reasoning and planning. Towards addressing this, we propose an inference-time tree search algorithm for LLM agents to explicitly perform exploration and multi-step planning in interactive web environments. It is the first tree search algorithm for LLM agents that shows effectiveness on realistic and complex web environments: on the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%.
0:20

LLM agents have demonstrated promise in their ability to automate computer tasks, but face challenges with multi-step reasoning and planning. Towards addressing this, we propose an inference-time tree search algorithm for LLM agents to explicitly perform exploration and multi-step planning in interactive web environments. It is the first tree search algorithm for LLM agents that shows effectiveness on realistic and complex web environments: on the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%.

Jing Yu Koh

124,878 görüntüleme • 2 yıl önce

I built a real estate AI Agent team with multi-agents using gpt-OSS and Firecrawl. It has 3 AI agents working together as a team: 1. Property Search Agent 2. Market Analysis Agent 3. Property Valuation Agent 100% Opensource with step-by-step tutorial.
0:44

I built a real estate AI Agent team with multi-agents using gpt-OSS and Firecrawl. It has 3 AI agents working together as a team: 1. Property Search Agent 2. Market Analysis Agent 3. Property Valuation Agent 100% Opensource with step-by-step tutorial.

Shubham Saboo

116,631 görüntüleme • 10 ay önce

We’re excited to announce an updated version of our Pro Search that can perform deeper research on more complex queries with multi-step reasoning, Wolfram|Alpha, and code execution.
0:43

We’re excited to announce an updated version of our Pro Search that can perform deeper research on more complex queries with multi-step reasoning, Wolfram|Alpha, and code execution.

Perplexity

321,053 görüntüleme • 2 yıl önce

I built an automated AI travel agency with multi-agents. It has 4 MCP AI agents working together as a team: 1. Google Maps Agent 2. Airbnb Booking Agent 3. Google Calendar Agent 4. Weather Agent 100% Opensource Code with step-by-step tutorial.
1:06

I built an automated AI travel agency with multi-agents. It has 4 MCP AI agents working together as a team: 1. Google Maps Agent 2. Airbnb Booking Agent 3. Google Calendar Agent 4. Weather Agent 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

138,924 görüntüleme • 1 yıl önce

Planning your next adventure just got smarter! Meet Qwen’s Travel Planning Assistant, built on a Multi-Agent architecture for efficient, dynamic trip planning with outstanding planning capabilities. It taps into real-world third-party tools to craft itineraries that think ahead and adapt in real time ✈️
0:29

Planning your next adventure just got smarter! Meet Qwen’s Travel Planning Assistant, built on a Multi-Agent architecture for efficient, dynamic trip planning with outstanding planning capabilities. It taps into real-world third-party tools to craft itineraries that think ahead and adapt in real time ✈️

Alibaba Group

81,058 görüntüleme • 8 ay önce

Group navigation, multi-stop trip planning, group stats, and more— riding together just got smarter with Road Trip Mode. #MoveOS5
0:28

Group navigation, multi-stop trip planning, group stats, and more— riding together just got smarter with Road Trip Mode. #MoveOS5

Ola Electric

12,574 görüntüleme • 1 yıl önce

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.
0:20

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

36,596 görüntüleme • 1 yıl önce

Introducing Verdent 1.5: the most powerful multi-agent AI coding tool. Seamless Multitasking with Context Preservation Isolated Workspaces Orchestration Parallel Multi-Agent Execution Smarter Planning, Better Collaboration
1:33

Introducing Verdent 1.5: the most powerful multi-agent AI coding tool. Seamless Multitasking with Context Preservation Isolated Workspaces Orchestration Parallel Multi-Agent Execution Smarter Planning, Better Collaboration

Verdent

10,656,873 görüntüleme • 6 ay önce

I just built a RAG Agent with web search using Cohere's ⌘R 7B model. 100% Opensource Code with step-by-step tutorial.
1:35

I just built a RAG Agent with web search using Cohere's ⌘R 7B model. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

47,032 görüntüleme • 1 yıl önce

Sharing our latest short course: Building and Evaluating Data Agents, created in collaboration with Snowflake and taught by Anupam Datta (Anupam Datta) and Josh Reini (Josh Reini). A data agent extracts data from sources such as files or databases, analyzes it, and provides insights and visualizes its findings. But most data agents struggle with reliability or can't handle multi-step reasoning. In this course, you'll learn to build, trace, and evaluate a multi-agent workflow that plans tasks, pulls context from structured and unstructured data, performs web search, and summarizes or visualizes the final results. Learn more and enroll for free!
3:20

Sharing our latest short course: Building and Evaluating Data Agents, created in collaboration with Snowflake and taught by Anupam Datta (Anupam Datta) and Josh Reini (Josh Reini). A data agent extracts data from sources such as files or databases, analyzes it, and provides insights and visualizes its findings. But most data agents struggle with reliability or can't handle multi-step reasoning. In this course, you'll learn to build, trace, and evaluate a multi-agent workflow that plans tasks, pulls context from structured and unstructured data, performs web search, and summarizes or visualizes the final results. Learn more and enroll for free!

DeepLearning.AI

40,745 görüntüleme • 9 ay önce

R2R from is an open-source agentic retrieval system that transforms RAG with multi-step reasoning across your data and the web.
0:44

R2R from is an open-source agentic retrieval system that transforms RAG with multi-step reasoning across your data and the web.

Y Combinator

23,251 görüntüleme • 1 yıl önce

Watch this ADK Agent powered by Gemma 4 31B use the Google Maps MCP Server to build a custom food tour in this demo 🍜📍 See the model in action with: -Multi-step reasoning (solving complex routes) -Multimodal logic (processing visuals and text) -Live data integration (direct connection to Google Maps)
1:12

Watch this ADK Agent powered by Gemma 4 31B use the Google Maps MCP Server to build a custom food tour in this demo 🍜📍 See the model in action with: -Multi-step reasoning (solving complex routes) -Multimodal logic (processing visuals and text) -Live data integration (direct connection to Google Maps)

Google AI Developers

28,084 görüntüleme • 2 ay önce

Meta PARTNR is a benchmark for planning and reasoning in embodied multi-agent tasks. This large-scale human and robot collaboration benchmark was core to our recent demos and also informs our work as scientists and engineers pushing this field of study forward.
1:21

Meta PARTNR is a benchmark for planning and reasoning in embodied multi-agent tasks. This large-scale human and robot collaboration benchmark was core to our recent demos and also informs our work as scientists and engineers pushing this field of study forward.

AI at Meta

33,607 görüntüleme • 1 yıl önce

We've added a new "reasoning" focus (beta) on Perplexity for Pro users. It will use the new OpenAI o1-mini. There is no search integration yet. The model is slow, and usage is limited because of rate limits. It is good for puzzles, math, and coding. Pro searches are your best way to use multi-step reasoning + web search.
0:27

We've added a new "reasoning" focus (beta) on Perplexity for Pro users. It will use the new OpenAI o1-mini. There is no search integration yet. The model is slow, and usage is limited because of rate limits. It is good for puzzles, math, and coding. Pro searches are your best way to use multi-step reasoning + web search.

Aravind Srinivas

288,789 görüntüleme • 1 yıl önce

Build a Local RAG Reasoning Agent with Qwen 3, using a Vector Database with Web Search for fallback. You can also choose Gemma 3 or DeepSeek R1. 100% free, local, and Opensource.
0:49

Build a Local RAG Reasoning Agent with Qwen 3, using a Vector Database with Web Search for fallback. You can also choose Gemma 3 or DeepSeek R1. 100% free, local, and Opensource.

Unwind AI

52,006 görüntüleme • 1 yıl önce

Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory
3:57

Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory

AK

19,923 görüntüleme • 10 ay önce