Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Collaborative Reasoner: a framework to improve collaborative reasoning in language models. Collaborative Reasoner paves the way for developing social agents that can partner with humans and other agents. Read the research paper and download the code.

AI at Meta

782,674 subscribers

58,387 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

11 Comments

PatD931 year ago

So you guys basically cracked AGI

SecBriefs | Making Cybersecurity Simple1 year ago

🤝 Interviewing with HR or non-technical managers? 🌟 Employers value clarity and confidence. Cybersecurity Dictionary for Everyone teaches you to explain cybersecurity concepts in a way everyone can understand. Build connections that matter! 🌟

ABE aka JONTY1 year ago

Congrats to the team behind Collaborative Reasoner! As a former Meta engineer, I’m excited to see a framework that truly advances LMs from solo solvers to genuine partners. How does CR handle conflict resolution when human and agent goals diverge?

Remilya🇹🇷💫1 year ago

So this is an SillyTavern grup chat for Ai agent things?

Michael R Dawley Jr1 year ago

this fits .... will try it our efforts at

-T3ch-1 year ago

ahahahahahah

Shaji Prathapan T P1 year ago

Now perfect.

An Hoang Ngo1 year ago

I wish there was a framework for looking at old profile review appeals.

craig1 year ago

Awesome, thanks

Jonas Weigand1 year ago

Exciting step forward.

RobKai 🇩🇪1 year ago

What happened to behemoth?

Related Videos

LM agents today primarily aim to automate tasks. Can we turn them into collaborative teammates? Introducing Collaborative Gym (Co-Gym), a framework for enabling & evaluating human-agent collaboration! I now get used to agents proactively seeking confirmation or my deep thinking.

LM agents today primarily aim to automate tasks. Can we turn them into collaborative teammates? Introducing Collaborative Gym (Co-Gym), a framework for enabling & evaluating human-agent collaboration! I now get used to agents proactively seeking confirmation or my deep thinking.

Yijia Shao

72,095 views • 1 year ago

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,214 views • 1 year ago

Do AI agents ask good questions? We built “Collaborative Battleship” to find out—and discovered that weaker LMs + Bayesian inference can beat GPT-5 at 1% of the cost. Paper, code & demos: Here's what we learned about building rational information-seeking agents... 🧵🔽

Do AI agents ask good questions? We built “Collaborative Battleship” to find out—and discovered that weaker LMs + Bayesian inference can beat GPT-5 at 1% of the cost. Paper, code & demos: Here's what we learned about building rational information-seeking agents... 🧵🔽

Gabe Grand

45,227 views • 7 months ago

✨ Introducing useAgent() A new primitive for the agentic application age. Connect ANY agent with your Frontend application. Drive intelligent interfaces & collaborative agents.

✨ Introducing useAgent() A new primitive for the agentic application age. Connect ANY agent with your Frontend application. Drive intelligent interfaces & collaborative agents.

CopilotKit🪁

72,687 views • 5 months ago

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

Box

227,222 views • 3 months ago

Introducing varg teams Collaborative mode for video generation. ✦ Create videos with AI agents ✦ Share assets and prompts ✦ Fork and remix any video Every video in varg is code - full end-to-end generated videos Built for teams making ads, social media, and in-app content

Introducing varg teams Collaborative mode for video generation. ✦ Create videos with AI agents ✦ Share assets and prompts ✦ Fork and remix any video Every video in varg is code - full end-to-end generated videos Built for teams making ads, social media, and in-app content

Alex Varga /✦

23,768 views • 7 days ago

this is wild turns out the best part of Figma MCP is that the agents are really good at FigJam now when I plan work with the agents, I get ✨ collaborative ✨ diagrams that are easy to read, easy to share, and easy to edit

this is wild turns out the best part of Figma MCP is that the agents are really good at FigJam now when I plan work with the agents, I get ✨ collaborative ✨ diagrams that are easy to read, easy to share, and easy to edit

Amelia Wattenberger 🪷

15,196 views • 2 months ago

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

introducing Ariana - the collaborative agentic IDE based on Claude Code - manage tasks with your team - give them to multiple coding agents with their own machine & branch - review with your team - agents merge for u comment "Better late than never" to get a build soon

Anicet

17,668 views • 10 months ago

2/ Plan Prism - 🥉3rd place AI agents that take PRDs and automatically improve them via multi-agent collaborative debate m AI agents to replace PMs ankit tandon Sunanda Saxena

2/ Plan Prism - 🥉3rd place AI agents that take PRDs and automatically improve them via multi-agent collaborative debate m AI agents to replace PMs ankit tandon Sunanda Saxena

Alex Reibman 🖇️

69,232 views • 1 year ago

📣 New paper: Emergence of Maps in the Memories of Blind Navigation Agents Humans have the ability to navigate poorly lit spaces by relying on touch and memory. Our research shows that blind AI agents can learn to do the same. Read the paper ➡️

📣 New paper: Emergence of Maps in the Memories of Blind Navigation Agents Humans have the ability to navigate poorly lit spaces by relying on touch and memory. Our research shows that blind AI agents can learn to do the same. Read the paper ➡️

AI at Meta

89,645 views • 3 years ago

Announcing Builder 2.0 We raised $67M to build collaborative coding for Claude and Codex - Start tasks from a local branch, Slack or Jira - Real-time collab between humans and agents - 100s of parallel agents code, test, review Reply "Builder" and I'll DM you 500 agent credits

Announcing Builder 2.0 We raised $67M to build collaborative coding for Claude and Codex - Start tasks from a local branch, Slack or Jira - Real-time collab between humans and agents - 100s of parallel agents code, test, review Reply "Builder" and I'll DM you 500 agent credits

Steve (Builder.io)

90,005,869 views • 1 month ago

Introducing Electric Agents! Agents are not compute. Agents are data. Multi-agent is a sync problem. Electric Agents is the first agent platform built on sync. Use it to build scalable, collaborative, long-lived multi-agent systems: 🧵👇

Introducing Electric Agents! Agents are not compute. Agents are data. Multi-agent is a sync problem. Electric Agents is the first agent platform built on sync. Use it to build scalable, collaborative, long-lived multi-agent systems: 🧵👇

Electric

70,835 views • 1 month ago

🤖 AI Agents vs Agentic AI: What’s the difference? We broke down the latest research paper on the conceptual taxonomy, use cases, and challenges of both. 🧠 AI Agents = simple automation ⚙️ Agentic AI = complex, collaborative goal-seeking 🎥 Watch the demo 📚 Get the TL;DR below 👇

🤖 AI Agents vs Agentic AI: What’s the difference? We broke down the latest research paper on the conceptual taxonomy, use cases, and challenges of both. 🧠 AI Agents = simple automation ⚙️ Agentic AI = complex, collaborative goal-seeking 🎥 Watch the demo 📚 Get the TL;DR below 👇

Masa

14,391 views • 1 year ago

Today we are proud to emerge from stealth as Collaborative Computing Inc. Our mission is to build collaborative computing environments for humans and AI that expand what we can achieve. Atelier is our first product.

Today we are proud to emerge from stealth as Collaborative Computing Inc. Our mission is to build collaborative computing environments for humans and AI that expand what we can achieve. Atelier is our first product.

Austin Huang

47,787 views • 4 months ago

Build smarter agents, together. This demo shows how projects in Gemini Enterprise provide a persistent space for your team and agents to work together on a project, with specific data, shared conversations, and a collaborative canvas →

Build smarter agents, together. This demo shows how projects in Gemini Enterprise provide a persistent space for your team and agents to work together on a project, with specific data, shared conversations, and a collaborative canvas →

Google Cloud

11,994 views • 24 days ago

Today, we’re excited to announce Dojo, a collaborative RL environment suite for computer use agents (CUA).

Today, we’re excited to announce Dojo, a collaborative RL environment suite for computer use agents (CUA).

Chakra Labs

52,958 views • 7 months ago

I present to you my latest fully vibeslopped "I didn't read the code" oeuvre: Jot A self-hosted collaborative markdown editor for you, your friends, and your agents. Like Google Docs, but worse. Try it with me here: Share a note, pick access (view/comment/edit), hand the link to a human or paste the CLI instructions into your agent. They can read, edit, and comment together in real-time.

I present to you my latest fully vibeslopped "I didn't read the code" oeuvre: Jot A self-hosted collaborative markdown editor for you, your friends, and your agents. Like Google Docs, but worse. Try it with me here: Share a note, pick access (view/comment/edit), hand the link to a human or paste the CLI instructions into your agent. They can read, edit, and comment together in real-time.

Mario Zechner

28,409 views • 2 months ago

The Aither LitePaper is Live! Discover the Agent Virtual Machine (AVM)—a groundbreaking execution layer for modular AI Agents, collaborative swarms, and tokenized intelligence. This is the foundation of a unified, scalable AI ecosystem. 📖 Read now:

The Aither LitePaper is Live! Discover the Agent Virtual Machine (AVM)—a groundbreaking execution layer for modular AI Agents, collaborative swarms, and tokenized intelligence. This is the foundation of a unified, scalable AI ecosystem. 📖 Read now:

Aither Protocol

88,820 views • 1 year ago

AI agents are becoming native users of software. Today, we’re kicking off Unveil Week with a broader vision than human-only collaborative features. Software itself needs to change for the age of agents.

AI agents are becoming native users of software. Today, we’re kicking off Unveil Week with a broader vision than human-only collaborative features. Software itself needs to change for the age of agents.

Liveblocks

648,189 views • 1 month ago