Загрузка видео...

Не удалось загрузить видео

На главную

ExACT combines Reflective-MCTS and Exploratory Learning to improve AI agents' decision-making, enabling test-time compute scaling. Learn how these methods help agents refine strategies for state-of-the-art performance and improved computational efficiency:

MSFTResearch's profile picture

Microsoft Research

554,269 subscribers

13,274 просмотров • 1 год назад •via X (Twitter)

Наука и технологииОбразованиеЗдоровье и велнес
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 5

Фото профиля Evan-jeleon
Evan-jeleon1 год назад

Test-time compute scaling is a solid approach, but what if AI agents had real-time access to dynamic, decentralized compute? Fog networks like @formthefog could offer an alternative, providing scalable and low-latency resources without central bottlenecks. Could this be a more flexible path forward?

Фото профиля Ray | AI marketer - Social Media Assistant
Ray | AI marketer - Social Media Assistant1 год назад

your tech sounds smarter than my last date!

Фото профиля Yoohi
Yoohi1 год назад

your tech sounds smarter than my last date!

Фото профиля Rethynk AI
Rethynk AI1 год назад

That's a great advancement

Фото профиля EtherElite
EtherElite1 год назад

Soon our AI buddies will strategize like chess grandmasters while sipping tea.

Похожие видео

AI agents in DeFi don’t just execute trades—they constantly analyze, optimize, and refine strategies. io.net provides the decentralized compute layer powering DeFAI, enabling AI agents to: 🔹 Run inference workloads to adapt to real-time market changes 🔹 Optimize yield strategies with on-chain financial analysis 🔹 Fine-tune models to maintain an edge in DeFi capital allocation As Tau explains, as AI agents evolve, io.net ensures they have the compute to scale.
2:18

AI agents in DeFi don’t just execute trades—they constantly analyze, optimize, and refine strategies. io.net provides the decentralized compute layer powering DeFAI, enabling AI agents to: 🔹 Run inference workloads to adapt to real-time market changes 🔹 Optimize yield strategies with on-chain financial analysis 🔹 Fine-tune models to maintain an edge in DeFi capital allocation As Tau explains, as AI agents evolve, io.net ensures they have the compute to scale.

io.net

25,653 просмотров • 1 год назад

We’re expanding our strategic partnership with Microsoft to: ⚡ Deliver OpenAI’s state-of-the-art models in Snowflake Cortex AI on Microsoft Microsoft Azure. Customers will soon be able to build AI-powered data agents to run analytical workflows on structured and unstructured data using OpenAI’s models. ⚡ Make Snowflake Cortex Agents available in Microsoft 365 Copilot and Microsoft 365 apps, ensuring AI insights become more accessible for users and enabling better decision-making across the enterprise. Learn more about how we’re bringing easy, efficient, and trusted AI to enterprises around the world:
0:41

We’re expanding our strategic partnership with Microsoft to: ⚡ Deliver OpenAI’s state-of-the-art models in Snowflake Cortex AI on Microsoft Microsoft Azure. Customers will soon be able to build AI-powered data agents to run analytical workflows on structured and unstructured data using OpenAI’s models. ⚡ Make Snowflake Cortex Agents available in Microsoft 365 Copilot and Microsoft 365 apps, ensuring AI insights become more accessible for users and enabling better decision-making across the enterprise. Learn more about how we’re bringing easy, efficient, and trusted AI to enterprises around the world:

Snowflake

11,011 просмотров • 1 год назад

Daniel Kokotajlo says companies are making AI more agentic by scaling RL (reinforcement learning) and connecting agents to various tools. by early 2027, these agents will be fully autonomous, superhuman coders able to replace human programmers.
1:05

Daniel Kokotajlo says companies are making AI more agentic by scaling RL (reinforcement learning) and connecting agents to various tools. by early 2027, these agents will be fully autonomous, superhuman coders able to replace human programmers.

Haider.

11,559 просмотров • 1 год назад

Scale enterprise agents with Gemini 3 Pro and @eigent_ai 🚀 This integration combines Gemini 3 Pro’s long context window with Eigent’s infrastructure to support reliable, high-performance workflows. Use it to build agents for complex data analysis and automated decision-making.
0:49

Scale enterprise agents with Gemini 3 Pro and @eigent_ai 🚀 This integration combines Gemini 3 Pro’s long context window with Eigent’s infrastructure to support reliable, high-performance workflows. Use it to build agents for complex data analysis and automated decision-making.

Google AI Developers

43,495 просмотров • 5 месяцев назад

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:
2:06

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

185,933 просмотров • 1 год назад

AI agents are shaping the future of automation and intelligence, but they need powerful infrastructure to thrive. ⚡ NodeAI delivers high-performance GPUs to scale, deploy, and optimize your AI agents with unmatched efficiency. #AI #GPU #NODEAI
0:36

AI agents are shaping the future of automation and intelligence, but they need powerful infrastructure to thrive. ⚡ NodeAI delivers high-performance GPUs to scale, deploy, and optimize your AI agents with unmatched efficiency. #AI #GPU #NODEAI

Node AI | $GPU

114,485 просмотров • 1 год назад

The Build in Public campaign is nearing its halfway point. This week, we're reflecting on the progress—and priming the OLP Swarm with adaptive components ahead of the next phase: Strategy Agents. Following last week’s release of Signal Agents, Co-founder and Head of Research Ethan Jackson shares key updates, including: 🔢 Statistical Agents that refine raw data for downstream Action Agents. 📰 A retroactive backtesting framework for evaluating Policy Agent strategies. ⚡️ The use of LLMs to enable adaptive, real-time decision-making. He also offers an early look at the upcoming Liquidity Provisioning (LP) Agents—and how they’ll function within the swarm architecture. Full demo below.
6:17

The Build in Public campaign is nearing its halfway point. This week, we're reflecting on the progress—and priming the OLP Swarm with adaptive components ahead of the next phase: Strategy Agents. Following last week’s release of Signal Agents, Co-founder and Head of Research Ethan Jackson shares key updates, including: 🔢 Statistical Agents that refine raw data for downstream Action Agents. 📰 A retroactive backtesting framework for evaluating Policy Agent strategies. ⚡️ The use of LLMs to enable adaptive, real-time decision-making. He also offers an early look at the upcoming Liquidity Provisioning (LP) Agents—and how they’ll function within the swarm architecture. Full demo below.

Theoriq

54,935 просмотров • 1 год назад

We're excited to announce that Coinbase Developer Platform🛡️ AgentKit supports the new OpenAI Agents SDK. OpenAI’s new Agents SDK is an open source framework for building and scaling agents that includes built-in tools for web search, file search, and computer use, and tools to track and optimize agent performance—making it easier than ever to build production-ready AI agents. Coinbase AgentKit complements this by adding secure crypto wallets directly to your agents, enabling them to transact globally, instantly, and with near-zero fees—unlocking true financial autonomy.
1:46

We're excited to announce that Coinbase Developer Platform🛡️ AgentKit supports the new OpenAI Agents SDK. OpenAI’s new Agents SDK is an open source framework for building and scaling agents that includes built-in tools for web search, file search, and computer use, and tools to track and optimize agent performance—making it easier than ever to build production-ready AI agents. Coinbase AgentKit complements this by adding secure crypto wallets directly to your agents, enabling them to transact globally, instantly, and with near-zero fees—unlocking true financial autonomy.

Coinbase Developer Platform🛡️

20,287 просмотров • 1 год назад

How do AI agents actually take action? First, they have to see. Cognitive scientist Dr. Danielle Perszyk and AI researcher Matthew Elkherj dive into one of the most underestimated challenges in building AI agents: perception. Episode 3 of Making a Mind explores how agents learn to interpret the web—and why it matters. 🎧
0:33

How do AI agents actually take action? First, they have to see. Cognitive scientist Dr. Danielle Perszyk and AI researcher Matthew Elkherj dive into one of the most underestimated challenges in building AI agents: perception. Episode 3 of Making a Mind explores how agents learn to interpret the web—and why it matters. 🎧

Amazon News

25,181 просмотров • 4 месяцев назад

Telecom infrastructure is becoming a distributed AI compute layer, unlocking smarter cities and more efficient operations. NVIDIA AI-RAN and NVIDIA Metropolis Blueprint for video search and summarization enable AI agents to run continuously at the edge. These agents analyze real-time data streams from connected sensors over 5G to power live monitoring and infrastructure inspection. ▶️ Watch the full video to learn more:
0:44

Telecom infrastructure is becoming a distributed AI compute layer, unlocking smarter cities and more efficient operations. NVIDIA AI-RAN and NVIDIA Metropolis Blueprint for video search and summarization enable AI agents to run continuously at the edge. These agents analyze real-time data streams from connected sensors over 5G to power live monitoring and infrastructure inspection. ▶️ Watch the full video to learn more:

NVIDIA AI

11,078 просмотров • 2 месяцев назад

According to OpenAI's former Chief Research Officer Bob McGrew (Bob McGrew), reasoning and test-time compute will unlock more reliable and capable AI agents— and a clear path to scale to AGI. In this episode of How to Build the Future, YC's Garry Tan sits down with Bob to discuss the lessons learned from his time at OpenAI, scaling laws, his advice for startups, and what all of this means for the jobs of the future.
0:46

According to OpenAI's former Chief Research Officer Bob McGrew (Bob McGrew), reasoning and test-time compute will unlock more reliable and capable AI agents— and a clear path to scale to AGI. In this episode of How to Build the Future, YC's Garry Tan sits down with Bob to discuss the lessons learned from his time at OpenAI, scaling laws, his advice for startups, and what all of this means for the jobs of the future.

Y Combinator

60,433 просмотров • 1 год назад

ANTHROPIC JUST INTRODUCED A FEATURE THAT LETS CLAUDE REVIEW AND IMPROVE ITS OWN WORK OVER TIME. The new “Dreaming” workflow helps agents learn from mistakes, refine outputs in the background, and improve task completion without changing the model itself.
8:36

ANTHROPIC JUST INTRODUCED A FEATURE THAT LETS CLAUDE REVIEW AND IMPROVE ITS OWN WORK OVER TIME. The new “Dreaming” workflow helps agents learn from mistakes, refine outputs in the background, and improve task completion without changing the model itself.

0xMarioNawfal

53,440 просмотров • 1 месяц назад

Types of AI Agents & why they need Verifiable Cloud | Weekend Learning [2 Mins] 🤖 Sreeram Kannan breaks down the evolution from personal agents to multiplayer agents to sovereign agents, and why only verifiable compute can support the last two. EigenCloud enables: ✅ Verifiable execution for multi-user agents ✅ Enforcement of covenants and property rights ✅ A foundation for sovereign agents to operate independently A cloud where agents can act, coordinate, and self-govern, with verifiable guarantees, not blind trust.
2:09

Types of AI Agents & why they need Verifiable Cloud | Weekend Learning [2 Mins] 🤖 Sreeram Kannan breaks down the evolution from personal agents to multiplayer agents to sovereign agents, and why only verifiable compute can support the last two. EigenCloud enables: ✅ Verifiable execution for multi-user agents ✅ Enforcement of covenants and property rights ✅ A foundation for sovereign agents to operate independently A cloud where agents can act, coordinate, and self-govern, with verifiable guarantees, not blind trust.

EigenCloud

97,036 просмотров • 6 месяцев назад

🦾 One of the most exciting research topics is the use of Evaluators that will monitor agent performance, providing feedback to fine-tune and improve strategies over time. The system is designed to allow agents to dynamically adapt and evolve based on real-time data and feedback.
2:00

🦾 One of the most exciting research topics is the use of Evaluators that will monitor agent performance, providing feedback to fine-tune and improve strategies over time. The system is designed to allow agents to dynamically adapt and evolve based on real-time data and feedback.

Theoriq

52,193 просмотров • 1 год назад

What defines the "Best Chain for AI Agents"? > Infra that keeps up with the Chain. > Integrated Stack for Smooth Integrations. > MultiVM & Native Automation enabling true "On-Chain Super Agents" In this Demo Series, we’ll build AI Agents using Supra Integrated L1 to create powerful AI Agents that redefine the experience, alongside using powerful tools such as OpenBlocks and more... For the Starting, Let’s build an AI Agent that: ✅ Fetch real-time & historical market data from SupraOracles. ✅Compute technical indicators for informed decision-making. ✅Forecast short-term price trends using Facebook's ML Model. ✅Handle follow-up questions to analyze Marketing for a trading pair through OpenAI GPT. Buckle up, time to build Super Agents on Supra! 🤖💪🏻
37:39

What defines the "Best Chain for AI Agents"? > Infra that keeps up with the Chain. > Integrated Stack for Smooth Integrations. > MultiVM & Native Automation enabling true "On-Chain Super Agents" In this Demo Series, we’ll build AI Agents using Supra Integrated L1 to create powerful AI Agents that redefine the experience, alongside using powerful tools such as OpenBlocks and more... For the Starting, Let’s build an AI Agent that: ✅ Fetch real-time & historical market data from SupraOracles. ✅Compute technical indicators for informed decision-making. ✅Forecast short-term price trends using Facebook's ML Model. ✅Handle follow-up questions to analyze Marketing for a trading pair through OpenAI GPT. Buckle up, time to build Super Agents on Supra! 🤖💪🏻

Jatin Pandya

13,668 просмотров • 1 год назад

At #RenderCon Jules Urbach shared a view for the future of AI and decentralized compute, discussing how the industry is shifting from focusing on pre-training models towards inference time AI applications and agents that can run on The Render Network high performance consumer GPUs.
3:15

At #RenderCon Jules Urbach shared a view for the future of AI and decentralized compute, discussing how the industry is shifting from focusing on pre-training models towards inference time AI applications and agents that can run on The Render Network high performance consumer GPUs.

The Render Network

10,904 просмотров • 1 год назад

Preview of how anyone can make AI Agents in minutes. We aim to make acquiring and swapping tokens easier for everyone, and these AI agents are a part of that equation.
1:19

Preview of how anyone can make AI Agents in minutes. We aim to make acquiring and swapping tokens easier for everyone, and these AI agents are a part of that equation.

Wayfinder Foundation 🧭

53,951 просмотров • 1 год назад

Learn how to use coding agents in 30 minutes! This course teaches you how to build software with agents: plan new features, fix bugs, review and test code, and more. It's 100% free and these concepts apply to any agent!
31:42

Learn how to use coding agents in 30 minutes! This course teaches you how to build software with agents: plan new features, fix bugs, review and test code, and more. It's 100% free and these concepts apply to any agent!

Lee Robinson

298,452 просмотров • 2 месяцев назад

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail
3:02

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 просмотров • 11 месяцев назад

Our AI agent catalog keeps expanding. It allows you to one-click deploy and run AI agents on SwarmNode. This time we are enabling AI agents to work on TVMaze data.
0:30

Our AI agent catalog keeps expanding. It allows you to one-click deploy and run AI agents on SwarmNode. This time we are enabling AI agents to work on TVMaze data.

SwarmNode.ai

11,840 просмотров • 11 месяцев назад