Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

What if we could have trustworthy agents that don't just write code, but also do research, understand multimodal content, and perform many practically useful tasks? Today at OpenHands, we released a new agent that gets SOTA or competitive performance on 8 diverse tasks.

OpenHands

11,502 subscribers

19,079 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля All Hands AI

All Hands AI1 год назад

What new sorts of things does this allow you to do? Here is an example: we asked the agent to do research about the OpenHands library, and create a promotional web site, grounded in citations so we were sure that the content was correct. It built this for us in one shot.

Фото профиля All Hands AI

All Hands AI1 год назад

How did we verify the agent's accuracy? We built VersaBench a benchmark that tests 5 capabilities: - Improving codebases (in 9 programming languages) - Building apps from scratch - Writing tests and fixing broken code - Researching new info - General business-relevant tasks

Фото профиля All Hands AI

All Hands AI1 год назад

What are the results? We achieved state-of-the-art performance of 5 of the 8 benchmarks we tested, and competitive performance on all the others. We believe this is the first time an agent has been demonstrated to be so broadly capable.

Фото профиля All Hands AI

All Hands AI1 год назад

How did we achieve this? Building on the strong base of OpenHands, which was already over 70% accuracy on SWE-Bench, we further added a small number of targeted tools: - Research w/ the @tavilyai search engine - Multimodal browsing with set-of-marks - Multimodal file access

Фото профиля All Hands AI

All Hands AI1 год назад

The paper about this versatile agent, OpenHands-Versa, was lead by @Aditya_Soni_8 at CMU, and you can read much more about the methodology: - His summary: - The paper: - Our blog:

Фото профиля All Hands AI

All Hands AI1 год назад

How can you access this new agent? It's available by default in the most recent version of OpenHands: - OpenHands Cloud: - Downloading OpenHands 0.41.0 or higher: We can't wait for your feedback on it!

Фото профиля SecBriefs | Making Cybersecurity Simple

SecBriefs | Making Cybersecurity Simple2 лет назад

Thinking about a career in cybersecurity but worried about your technical background? Don't be! 💡 Many roles value your problem-solving, analytical, & communication skills. 🕵️‍♀️ "Cybersecurity Dictionary for Everyone" is a good start, available on Amazon:

Фото профиля David J. Alba

David J. Alba1 год назад

Congrats on the release! We need to make some noise so Versabench gets the standard across labs on new models evaluation. Excited to try it 🫶

Фото профиля Abeansits

Abeansits1 год назад

amazing release! congrats to the team

Фото профиля Christopher

Christopher1 год назад

Hi again, sorry I’ve been digging into the new Versa Agent as planned but I can’t seem to find a link to the Benchmark. Has it been released publicly and I’m just missing it somehow? Thank you.

Похожие видео

We are releasing 4M-21 with a permissive license, including its source code and trained models. It's a pretty effective multimodal model that solves 10s of tasks & modalities. See the demo code, sample results, and the tokenizers of diverse modalities on the website. IMO, the multitask learning aspect of multimodal models has really taken a step forward. We can train a single model on many diverse tasks with ~SOTA accuracy. But a long way to go in terms of transfer/emergence. 🌐 ⌨️ Joint work w/ EPFL Apple.

We are releasing 4M-21 with a permissive license, including its source code and trained models. It's a pretty effective multimodal model that solves 10s of tasks & modalities. See the demo code, sample results, and the tokenizers of diverse modalities on the website. IMO, the multitask learning aspect of multimodal models has really taken a step forward. We can train a single model on many diverse tasks with ~SOTA accuracy. But a long way to go in terms of transfer/emergence. 🌐 ⌨️ Joint work w/ EPFL Apple.

Amir Zamir

69,610 просмотров • 2 лет назад

You can create an AI Agent that answers your email with a few clicks. 1. Go to ChatLLM ( 2. Click on AI Engineer 3. Select Create an AI Agent 4. Choose the Email Answering Agent ChatLLM will do the rest: it will code, test, and deploy the agent for you. You can also create a custom agent in English. The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025. Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions. That's where we'll see agents explode, and I'm here for it.

You can create an AI Agent that answers your email with a few clicks. 1. Go to ChatLLM ( 2. Click on AI Engineer 3. Select Create an AI Agent 4. Choose the Email Answering Agent ChatLLM will do the rest: it will code, test, and deploy the agent for you. You can also create a custom agent in English. The Agent Economy is coming (somebody should write a book and use this title.) We are going to see examples like this, times 1,000 in 2025. Just think about how many repetitive tasks you perform every day. Some of these tasks are involved enough that we couldn't automate them with pre-AI solutions. That's where we'll see agents explode, and I'm here for it.

Santiago

79,974 просмотров • 1 год назад

Sure, AWS DevOps Agent just went GA, but we added a bunch of features at the same time, including Custom Skills, Learned Skills, Code Indexing - just to name a few! If you have 30 seconds, you can see the new On-Demand SRE Tasks in action, which can help you with the endless variety of operational tasks that come up. More in the blog!

Sure, AWS DevOps Agent just went GA, but we added a bunch of features at the same time, including Custom Skills, Learned Skills, Code Indexing - just to name a few! If you have 30 seconds, you can see the new On-Demand SRE Tasks in action, which can help you with the endless variety of operational tasks that come up. More in the blog!

David Yanacek

20,981 просмотров • 6 месяцев назад

We finished evaluating π0.7, our new model at Physical Intelligence. What I'm most excited about with π0.7 is that it's starting to show some surprising emergent compositional generalization, being able to both perform complex tasks and learn new tasks just from instructions.

We finished evaluating π0.7, our new model at Physical Intelligence. What I'm most excited about with π0.7 is that it's starting to show some surprising emergent compositional generalization, being able to both perform complex tasks and learn new tasks just from instructions.

Sergey Levine

61,470 просмотров • 5 месяцев назад

Today we are launching the next phase of AI reasoning development with Founders Fund, Franklin Templeton, Pantera Capital, Fireworks AI, OpenRouter, OpenHands, Dedalus Labs, alphaXiv, and more. AI is advancing at a relentless pace, but there are many reasoning capabilities we have yet to discover. Announcing Arena—an evaluation-driven platform for ideation, prototyping, and high-quality data generation—with top AI developers advancing SOTA performance on real-world enterprise reasoning tasks.

Today we are launching the next phase of AI reasoning development with Founders Fund, Franklin Templeton, Pantera Capital, Fireworks AI, OpenRouter, OpenHands, Dedalus Labs, alphaXiv, and more. AI is advancing at a relentless pace, but there are many reasoning capabilities we have yet to discover. Announcing Arena—an evaluation-driven platform for ideation, prototyping, and high-quality data generation—with top AI developers advancing SOTA performance on real-world enterprise reasoning tasks.

Sentient

272,779 просмотров • 7 месяцев назад

New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks:

New course: Building Coding Agents with Tool Execution, taught by Tereza Tizkova and Fra from E2B. Most AI agents are limited to predefined function calls. This short course teaches you to build agents that write and execute code to accomplish tasks, accessing entire programming language ecosystems instead of being restricted to a fixed set of tools. You'll learn to run agent-generated code safely in sandboxed cloud environments that protect your systems from harmful operations. Skills you'll gain: - Build agents that write and execute code, manage files, and handle errors autonomously through feedback loops - Run agent code safely in E2B cloud sandboxes and understand tradeoffs between local, containerized, and cloud execution - Create a data analyst agent that explores visualizes data with Pandas - Create a full-stack agent that builds complete Next.js web applications Join and build agents that code their way through complex tasks:

Andrew Ng

204,552 просмотров • 10 месяцев назад

Game development remains one of the most-requested, and most-challenging, categories on Arena. Wayne Chi, PhD candidate at Carnegie Mellon University and research intern at Arena, just walked us through GameDevBench: a benchmark built from real tutorials that turns game development into verifiable, deterministic tasks. How do top frontier models perform on tasks a human beginner could complete in under an hour, and is the biggest bottleneck coding or multimodal understanding? Check out Wayne’s full talk to hear results and learn more about GameDevBench:

Game development remains one of the most-requested, and most-challenging, categories on Arena. Wayne Chi, PhD candidate at Carnegie Mellon University and research intern at Arena, just walked us through GameDevBench: a benchmark built from real tutorials that turns game development into verifiable, deterministic tasks. How do top frontier models perform on tasks a human beginner could complete in under an hour, and is the biggest bottleneck coding or multimodal understanding? Check out Wayne’s full talk to hear results and learn more about GameDevBench:

Arena.ai

17,370 просмотров • 1 месяц назад

Google just unveiled a new project that shows how AI Agents are coming for full browser and computer use. This opens up AI to any of the laborious knowledge tasks that we do today. Most importantly, it lets us automate work that we never had even contemplated before.

Google just unveiled a new project that shows how AI Agents are coming for full browser and computer use. This opens up AI to any of the laborious knowledge tasks that we do today. Most importantly, it lets us automate work that we never had even contemplated before.

Aaron Levie

145,442 просмотров • 1 год назад

We saw special agents perform special tasks and got amazed 🤯🤯 But the most special agent out of all is our Agent UNFK and he has not only made a meme song on unfk but also performed on it ✨️ My paper machine craft🔮 (Time : 20+ hours across 3 days) #UNFKearth $UNFK

We saw special agents perform special tasks and got amazed 🤯🤯 But the most special agent out of all is our Agent UNFK and he has not only made a meme song on unfk but also performed on it ✨️ My paper machine craft🔮 (Time : 20+ hours across 3 days) #UNFKearth $UNFK

rise

35,222 просмотров • 2 лет назад

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

✨New LangChain Academy Course: Learn to build with LangSmith Agent Builder 🪄 Learn how to build your own agents with LangSmith Agent Builder. Anyone can now build agents for complex daily tasks, without writing code. We built Agent Builder for anyone whose day gets swallowed by routine work. The research, follow-ups, updates, scheduling, and status checks that are essential to your operations, but quickly take over your calendar. Agent Builder is different from traditional workflow automations. You don’t need to map every step, tinker with if-this-then-that branching, or babysit dependencies. You just give it feedback like you would a teammate, and the agent learns using its memory. In this quickstart course, you'll learn how to: - Build an email agent - Understand what agents can do - Improve your agent - Set up triggers and your Agent Inbox Enroll for free ➡️

LangChain

26,513 просмотров • 8 месяцев назад

Tedros: "[The WHO] is working... to understand how misinformation and disinformation spreads... and what we can do to counter this problem." "But we must also make sure that when when we seek the trust of others, we are ourselves trustworthy." On a scale of 0-100, how "trustworthy" do you find Tedros and the WHO? 🤔

Tedros: "[The WHO] is working... to understand how misinformation and disinformation spreads... and what we can do to counter this problem." "But we must also make sure that when when we seek the trust of others, we are ourselves trustworthy." On a scale of 0-100, how "trustworthy" do you find Tedros and the WHO? 🤔

Wide Awake Media

86,445 просмотров • 1 год назад

Progress in open models is keeping Big AI labs up at night, and I'm here for it! We have a brand new open-weight multimodal model optimized for long-horizon tasks. This model is really good at something: it can work on tasks that keep evolving over time. • 280B total parameters, but only 16B active • 512K context window • Understands text, images, and audio • Strong reasoning, coding, and tool use But the best of all: the model learns and adapts to new information! Imagine you start running an agent today to solve a problem, and while it's working, you get new information that changes the initial conditions, or you change your mind. The agents you run today don't have issues with short tasks and goals that don't change, but reality is messy, and that makes it hard for long-horizon agents to succeed. The new dots3-note Preview model introduces TEMPO. TEMPO is a new reinforcement learning technique that lets the model periodically pause and critique its own progress. Basically, from time to time, the agent asks itself: "Am I getting closer to the goal, or am I wasting my time?" The same model switches between actor and critic. The actor works on the problem. The critic looks at the current state, reasons about how much progress it has made, and determines what should happen next. TEMPO gives the model feedback along the way. This is huge for any agent that can work on long-horizon tasks without wasting its time.

Santiago

80,792 просмотров • 1 месяц назад

Hello!, we've been silent for a while. A thread🧵: What we have shipped and what we are shipping today Today, we announce that we're upgrading CranL to be fully Agentic. Where your Agent writes code, commits and PRs. Create an account in CranL And deploy. We're Agent-Ready since our MCP/CLI allows agent to perform +450 actions on our services!

Hello!, we've been silent for a while. A thread🧵: What we have shipped and what we are shipping today Today, we announce that we're upgrading CranL to be fully Agentic. Where your Agent writes code, commits and PRs. Create an account in CranL And deploy. We're Agent-Ready since our MCP/CLI allows agent to perform +450 actions on our services!

CranL

40,722 просмотров • 5 дней назад

π0.7 handles diverse prompts that don't just say what to do, but also how to do it, including rich language and multimodal information, such as visual subgoal images. At test time, these images can be produced by a lightweight world model.

π0.7 handles diverse prompts that don't just say what to do, but also how to do it, including rich language and multimodal information, such as visual subgoal images. At test time, these images can be produced by a lightweight world model.

Physical Intelligence

34,576 просмотров • 5 месяцев назад

Tencent announces AppAgent Multimodal Agents as Smartphone Users paper page: Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning method. The agent learns to navigate and use new apps either through autonomous exploration or by observing human demonstrations. This process generates a knowledge base that the agent refers to for executing complex tasks across different applications. To demonstrate the practicality of our agent, we conducted extensive testing over 50 tasks in 10 different applications, including social media, email, maps, shopping, and sophisticated image editing tools. The results affirm our agent's proficiency in handling a diverse array of high-level tasks.

Tencent announces AppAgent Multimodal Agents as Smartphone Users paper page: Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning method. The agent learns to navigate and use new apps either through autonomous exploration or by observing human demonstrations. This process generates a knowledge base that the agent refers to for executing complex tasks across different applications. To demonstrate the practicality of our agent, we conducted extensive testing over 50 tasks in 10 different applications, including social media, email, maps, shopping, and sophisticated image editing tools. The results affirm our agent's proficiency in handling a diverse array of high-level tasks.

AK

343,997 просмотров • 2 лет назад

📁 Dario Amodei, CEO of Anthropic, says we are approaching a country of geniuses inside a data center. AI agents could soon surpass most humans at most tasks and coordinate at superhuman speed. That could cure disease and lift billions out of poverty. Or it could amplify misuse, autonomy and economic disruption at a scale we have never faced.

📁 Dario Amodei, CEO of Anthropic, says we are approaching a country of geniuses inside a data center. AI agents could soon surpass most humans at most tasks and coordinate at superhuman speed. That could cure disease and lift billions out of poverty. Or it could amplify misuse, autonomy and economic disruption at a scale we have never faced.

Jon Hernandez

22,350 просмотров • 7 месяцев назад

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

elvis

104,217 просмотров • 4 месяцев назад

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation

For the first time in human history, we are teaching a Foundation Model to master the diverse tasks of medicinal chemists, biologists, and computational scientists all in one place. In our latest collaboration with Liquid AI, we are moving away from fragmented, specialized tools toward a single, super-intelligent model. What surprised me most? This model isn't just performing at reasonable levels—it has started outperforming specialist models across physics-based tasks, imaging, and longitudinal data. Why this changes everything: -Synergy over Specialization: Fine-tuning on specific tasks has unlocked unexpected capabilities in synergetic areas, opening a new frontier in multimodal AI research. -Zero-Shot Potential: We are building a model that can perform out-of-scope tasks, moving us closer to an "AI deity" for drug discovery. -Quality First: The goal isn't just to bypass regulations to save time; it’s about using these synergies to develop better, more effective drugs. We are no longer just looking at linear regression or simple text; we are looking at the future of how humanity fights disease. #LiquidAI #InsilicoMedicine #GenerativeAI #DrugDiscovery #DeepTech #BiotechInnovation

Alex Zhavoronkov, PhD (aka Aleksandrs Zavoronkovs)

10,544 просмотров • 6 месяцев назад