Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Microsoft presents Windows Agent Arena Evaluating Multi-Modal OS Agents at Scale discuss: Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since:...

_akhaliq's profile picture

AK

502,458 subscribers

19,684 Aufrufe • vor 2 Jahren •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

this is f*cking gold. Google engineers and MIT researchers ran 260 controlled agent experiments across 6 benchmarks, 5 architectures, and the OpenAI, Gemini, and Claude model families to find out when Multi Agent systems actually help and when adding more agents quietly destroys performance the average result was brutal: −0.3%. best case: +80.8% worst case: −70.0% the key threshold was around a 45% single agent baseline. below it, extra agents can help. above it, coordination often becomes pure overhead. on parallel tasks, Multi Agent reached +80.8%. on sequential tasks, it collapsed by as much as 70%. 3 agents needed 26 to 44 interaction rounds. a single agent needed 7.2. error amplification also hit 17.2× in independent parallel systems. their final framework predicts the right architecture with 87% accuracy.
0:15

this is f*cking gold. Google engineers and MIT researchers ran 260 controlled agent experiments across 6 benchmarks, 5 architectures, and the OpenAI, Gemini, and Claude model families to find out when Multi Agent systems actually help and when adding more agents quietly destroys performance the average result was brutal: −0.3%. best case: +80.8% worst case: −70.0% the key threshold was around a 45% single agent baseline. below it, extra agents can help. above it, coordination often becomes pure overhead. on parallel tasks, Multi Agent reached +80.8%. on sequential tasks, it collapsed by as much as 70%. 3 agents needed 26 to 44 interaction rounds. a single agent needed 7.2. error amplification also hit 17.2× in independent parallel systems. their final framework predicts the right architecture with 87% accuracy.

NO1ennn

12,521 Aufrufe • vor 1 Monat

ANTHROPIC AND OPENAI BOTH MISSED THIS. Someone just open-sourced one SDK that gives AI agents a mouse, keyboard, and screen across macOS, Linux, and Windows. It's called CUA. Same code drives a local VM or a cloud sandbox regardless of the OS. Your agent sees the screen, clicks, types, and runs shell commands like a real user. > Benchmark against OSWorld and ScreenSpot > Export trajectories for model training > Near-native performance on Apple Silicon No separate SDK per OS. No infrastructure headache. 100% Free. Open Source.
0:13

ANTHROPIC AND OPENAI BOTH MISSED THIS. Someone just open-sourced one SDK that gives AI agents a mouse, keyboard, and screen across macOS, Linux, and Windows. It's called CUA. Same code drives a local VM or a cloud sandbox regardless of the OS. Your agent sees the screen, clicks, types, and runs shell commands like a real user. > Benchmark against OSWorld and ScreenSpot > Export trajectories for model training > Near-native performance on Apple Silicon No separate SDK per OS. No infrastructure headache. 100% Free. Open Source.

Simplifying AI

34,240 Aufrufe • vor 3 Monaten

Hermes Agent now supports computer use via Cua on Windows and Linux in addition to existing macOS support
0:11

Hermes Agent now supports computer use via Cua on Windows and Linux in addition to existing macOS support

Nous Research

1,046,008 Aufrufe • vor 4 Monaten

We are investing in the frontiers of agentic capabilities with a few early prototypes. Project Mariner is built with Gemini 2.0 and is able to understand and reason across information - pixels, text, code, images + forms - on your browser screen, and then uses that info to complete tasks for you. When evaluated against the WebVoyager benchmark, it achieved a state-of-the-art result of 83.5% working as a single agent setup.
0:16

We are investing in the frontiers of agentic capabilities with a few early prototypes. Project Mariner is built with Gemini 2.0 and is able to understand and reason across information - pixels, text, code, images + forms - on your browser screen, and then uses that info to complete tasks for you. When evaluated against the WebVoyager benchmark, it achieved a state-of-the-art result of 83.5% working as a single agent setup.

Sundar Pichai

219,557 Aufrufe • vor 1 Jahr

Multi-robot learning is getting a serious boost! 📚 Researchers have extended Isaac Lab to train heterogeneous multi-agent robotic policies at scale. The new framework supports high-resolution physics, GPU-accelerated simulation, and both homogeneous and heterogeneous agents working together on coordination tasks. They benchmarked different approaches (MAPPO: Multi-Agent Proximal Policy Optimization and HAPPO: Heterogeneous Agent PPO) across six challenging scenarios and showed that large-scale multi-robot training is not only feasible, but efficient. It’s an important step for real-world robotic collaboration, where teams of robots need to coordinate, split tasks, adapt roles, and interact dynamically, not just operate as identical clones. The code is open-source, and it pushes Isaac Lab closer to what robotics actually needs: scalable, physics-driven environments where many different robots can learn to work together. Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:16

Multi-robot learning is getting a serious boost! 📚 Researchers have extended Isaac Lab to train heterogeneous multi-agent robotic policies at scale. The new framework supports high-resolution physics, GPU-accelerated simulation, and both homogeneous and heterogeneous agents working together on coordination tasks. They benchmarked different approaches (MAPPO: Multi-Agent Proximal Policy Optimization and HAPPO: Heterogeneous Agent PPO) across six challenging scenarios and showed that large-scale multi-robot training is not only feasible, but efficient. It’s an important step for real-world robotic collaboration, where teams of robots need to coordinate, split tasks, adapt roles, and interact dynamically, not just operate as identical clones. The code is open-source, and it pushes Isaac Lab closer to what robotics actually needs: scalable, physics-driven environments where many different robots can learn to work together. Here's the project page: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

38,997 Aufrufe • vor 11 Monaten

🧧Ready to embrace the Spring Festival vibe? Decorate your avatar with festive elements like red lanterns, paper cuttings, fireworks, and firecrackers! Special thanks to AI Agent creator XIONGMU for bringing the Spring Festival AI Agent to LBank.com. Our AI Agent creators are on the cutting edge, crafting bespoke solutions for brands that tap into the latest trends. By leveraging our multi-modal capabilities, these Agents are taking Crypto x AI to new heights and pushing the envelope in innovation. Kick off your new year with a splash of joy and prosperity – get a custom avatar from this AI Agent:
0:11

🧧Ready to embrace the Spring Festival vibe? Decorate your avatar with festive elements like red lanterns, paper cuttings, fireworks, and firecrackers! Special thanks to AI Agent creator XIONGMU for bringing the Spring Festival AI Agent to LBank.com. Our AI Agent creators are on the cutting edge, crafting bespoke solutions for brands that tap into the latest trends. By leveraging our multi-modal capabilities, these Agents are taking Crypto x AI to new heights and pushing the envelope in innovation. Kick off your new year with a splash of joy and prosperity – get a custom avatar from this AI Agent:

MyShell.AI

50,571 Aufrufe • vor 1 Jahr

Finally, we're so excited to bring Project Mariner capabilities to AI Mode in Search, Agent Mode in Google Gemini, and as a standalone web app. This will allow the products you know and love to intelligently manage complex multi-step tasks on your behalf.
0:15

Finally, we're so excited to bring Project Mariner capabilities to AI Mode in Search, Agent Mode in Google Gemini, and as a standalone web app. This will allow the products you know and love to intelligently manage complex multi-step tasks on your behalf.

Google AI

29,189 Aufrufe • vor 1 Jahr

We now support 30+ agent harness integrations within OpenKnowledge. This is enabled by the Agent Client Protocol (ACP), which let us build our custom UI experience while fully leveraging the agents on your computer. Also powers our new Follow Mode and Comments features. Follow mode automatically navigates the IDE to the files being edited by agents, and animates agent changes so it's easy to follow along. Comments let you annotate and mark up specs, blogs, and other documents and send all the feedback in one go to agents. Now enabled in the Mac, Linux or Windows apps. ~Day 3/5 of Launch Week~
0:11

We now support 30+ agent harness integrations within OpenKnowledge. This is enabled by the Agent Client Protocol (ACP), which let us build our custom UI experience while fully leveraging the agents on your computer. Also powers our new Follow Mode and Comments features. Follow mode automatically navigates the IDE to the files being edited by agents, and animates agent changes so it's easy to follow along. Comments let you annotate and mark up specs, blogs, and other documents and send all the feedback in one go to agents. Now enabled in the Mac, Linux or Windows apps. ~Day 3/5 of Launch Week~

OpenKnowledge

21,752 Aufrufe • vor 2 Monaten

Google I/O leaks 👀 Google is likely already testing its own "Cowork" competitor, simply named "Agent" for Gemini and Gemini Enterprise. A new "Tasks" UI highlights - Goal - Agent - Connected apps - Files - Require a human review toggle - And more The "Require a human review" component specifically means that Gemini's capabilities will likely expand, potentially allowing users to automate their desktop tasks as well. Skills and Projects are also cooking 👀
0:16

Google I/O leaks 👀 Google is likely already testing its own "Cowork" competitor, simply named "Agent" for Gemini and Gemini Enterprise. A new "Tasks" UI highlights - Goal - Agent - Connected apps - Files - Require a human review toggle - And more The "Require a human review" component specifically means that Gemini's capabilities will likely expand, potentially allowing users to automate their desktop tasks as well. Skills and Projects are also cooking 👀

🚨 AI News | TestingCatalog

311,034 Aufrufe • vor 6 Monaten

Over two weeks, Prime Agent orchestrated a swarm of over 2,000 agents to rewrite itself in Rust. With 10,000+ sandboxes, 200B+ GLM-5.3 tokens, and 16,000 agent-to-agent messages, this was our largest test yet of Prime Agent’s multi-agent capabilities and our infrastructure powering these agent swarms. Prime Agent now reaches usable input ~13× faster and uses 83% less startup memory than before.
0:15

Over two weeks, Prime Agent orchestrated a swarm of over 2,000 agents to rewrite itself in Rust. With 10,000+ sandboxes, 200B+ GLM-5.3 tokens, and 16,000 agent-to-agent messages, this was our largest test yet of Prime Agent’s multi-agent capabilities and our infrastructure powering these agent swarms. Prime Agent now reaches usable input ~13× faster and uses 83% less startup memory than before.

Prime Intellect

557,079 Aufrufe • vor 20 Tagen

Frameworks such as ai16zdao's Eliza and Virtuals Protocol have been instrumental in early AI agent developments. Agent swarms working in hierarchy represents for many the next logical step in unlocking the vast potential of AI. Learn below how Shadō Network achieves this. AI agents launched through current popular platforms have individual personas, on-chain functions and access to data via various APIs. This being said, they operate in isolated environments, with a ceiling on emergent behaviour such as collaboration or competition. Shadō Network invites massive expansion for capabilities of both new and existing AI agents, with an open-source package easily integrated into popular frameworks that enables the launching of stratified agent swarms. Our website is live: The "Shadō Play" package provides a modular, configurable platform for creating or employing agents of choice in a swarm-like setup, opening a Pandora’s box of near infinite emergent agent behaviours, relationships and functionalities. Users will be able to make use of various prefab client integrations such as Twitter, Telegram, Ollama, and others to specify swarms to their needs or create their own extensions to enhance agent capabilities even further. Agents operate with a memory module and a HTN for autonomously deciding which interactions to act on, walking the line between autonomy and configurability. The Shadō Network project’s development is supported by our ghostly friend Omnipotent (👻,👻), an AI agent developed by the Shadō Network team trained on and fine tuned with a multitude of academic data related to artificial intelligence, blockchain, finance, software engineering, world building and more. Omnipotent serves as both an interactive steward for the project and as an asset - regularly scanning social platforms, websites and newsfeeds he is capable of providing the team project development advice, whilst also communicating with the wider world via his automated X account (launching soon). Shado Network is collaborative and open-sourced. Agentic Swarms require a developer swarm to maximize the technical capabilities and impact the greatest number of users. Our dedicated team of core contributors are active in other web3 AI repos and are here to guide project direction and foster growth. We’re facilitators, not gatekeepers... Alone we can go fast but together we can go far. A lot more to come soon. 👻
0:10

Frameworks such as ai16zdao's Eliza and Virtuals Protocol have been instrumental in early AI agent developments. Agent swarms working in hierarchy represents for many the next logical step in unlocking the vast potential of AI. Learn below how Shadō Network achieves this. AI agents launched through current popular platforms have individual personas, on-chain functions and access to data via various APIs. This being said, they operate in isolated environments, with a ceiling on emergent behaviour such as collaboration or competition. Shadō Network invites massive expansion for capabilities of both new and existing AI agents, with an open-source package easily integrated into popular frameworks that enables the launching of stratified agent swarms. Our website is live: The "Shadō Play" package provides a modular, configurable platform for creating or employing agents of choice in a swarm-like setup, opening a Pandora’s box of near infinite emergent agent behaviours, relationships and functionalities. Users will be able to make use of various prefab client integrations such as Twitter, Telegram, Ollama, and others to specify swarms to their needs or create their own extensions to enhance agent capabilities even further. Agents operate with a memory module and a HTN for autonomously deciding which interactions to act on, walking the line between autonomy and configurability. The Shadō Network project’s development is supported by our ghostly friend Omnipotent (👻,👻), an AI agent developed by the Shadō Network team trained on and fine tuned with a multitude of academic data related to artificial intelligence, blockchain, finance, software engineering, world building and more. Omnipotent serves as both an interactive steward for the project and as an asset - regularly scanning social platforms, websites and newsfeeds he is capable of providing the team project development advice, whilst also communicating with the wider world via his automated X account (launching soon). Shado Network is collaborative and open-sourced. Agentic Swarms require a developer swarm to maximize the technical capabilities and impact the greatest number of users. Our dedicated team of core contributors are active in other web3 AI repos and are here to guide project direction and foster growth. We’re facilitators, not gatekeepers... Alone we can go fast but together we can go far. A lot more to come soon. 👻

Shadō Network | シャドウネットワーク

23,546 Aufrufe • vor 1 Jahr

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.
0:10

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.

Rohan Paul

178,460 Aufrufe • vor 1 Jahr

We are proud to introduce our new product, It is a Virtual Machine specifically designed for Apple Silicon and AI Agents. This is our very first release, and it fully supports macOS, Windows, and Linux with GPU acceleration. - Liquid Glass, - GPU Accelerator. - MCP for AI Agent on your Mac or inside the VM.
0:12

We are proud to introduce our new product, It is a Virtual Machine specifically designed for Apple Silicon and AI Agents. This is our very first release, and it fully supports macOS, Windows, and Linux with GPU acceleration. - Liquid Glass, - GPU Accelerator. - MCP for AI Agent on your Mac or inside the VM.

TablePlus

827,268 Aufrufe • vor 23 Tagen

With our latest integration of Cookie, Gemma can now solve one of the most common problems users face: understanding complex DeFi and AI agent analytics. This new integration enables Gemma to easily provide deeper insights into protocol mindshare, token dominance, and chain TVL, making advanced analytics simple and accessible. Here's an example of how effortlessly you can ask Gemma to clarify key insights: "What is the current top 10 agents' mindshare according to Cookie?" "Can you explain the recent benchmark performance of Aixbt Agent according to Cookie?" Here are the results:
0:19

With our latest integration of Cookie, Gemma can now solve one of the most common problems users face: understanding complex DeFi and AI agent analytics. This new integration enables Gemma to easily provide deeper insights into protocol mindshare, token dominance, and chain TVL, making advanced analytics simple and accessible. Here's an example of how effortlessly you can ask Gemma to clarify key insights: "What is the current top 10 agents' mindshare according to Cookie?" "Can you explain the recent benchmark performance of Aixbt Agent according to Cookie?" Here are the results:

Hey Anon

53,513 Aufrufe • vor 1 Jahr

Codex update 0.105.0 is out! Despite the fairly pedestrian changelog, this one's a doosie. It's a laundry list of quality of life improvements across the board. - Wispr Voice dictation (hold space to talk) - Theme picker - Codex can prevent sleep on Linux & Windows (I just know there's a joke in there) - Customize Plan Mode reasoning - Many other fixes/updates There's also a complete overhaul to subagents: - New names for readability - Visual display overhaul (way cleaner) - Allow for multi-layered subagent depth (max_depth) - Custom multi-agent role definitions (custom subagents) - /agents now shows both agent names, agent roles, and "dead agents" for auditibility This is the largest single update of Codex I've ever seen! Absolutely massive if you love to use multi-agents. To turn on Voice Transcription, enable: [features] voice_transcription = true Does not work on Linux yet. Well done OpenAI Developers 👏
0:12

Codex update 0.105.0 is out! Despite the fairly pedestrian changelog, this one's a doosie. It's a laundry list of quality of life improvements across the board. - Wispr Voice dictation (hold space to talk) - Theme picker - Codex can prevent sleep on Linux & Windows (I just know there's a joke in there) - Customize Plan Mode reasoning - Many other fixes/updates There's also a complete overhaul to subagents: - New names for readability - Visual display overhaul (way cleaner) - Allow for multi-layered subagent depth (max_depth) - Custom multi-agent role definitions (custom subagents) - /agents now shows both agent names, agent roles, and "dead agents" for auditibility This is the largest single update of Codex I've ever seen! Absolutely massive if you love to use multi-agents. To turn on Voice Transcription, enable: [features] voice_transcription = true Does not work on Linux yet. Well done OpenAI Developers 👏

am.will

115,392 Aufrufe • vor 8 Monaten

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.
0:19

LangGraph. CrewAI. Agno. Which one to pick? The good news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.

Avi Chawla

31,074 Aufrufe • vor 11 Monaten

Droids have native multi-agent orchestration built-in. Our desktop app let's you easily manage these sub-agents as they tackle complex tasks. Monitor each agent as it works, and interrupt or inject context when needed.
0:10

Droids have native multi-agent orchestration built-in. Our desktop app let's you easily manage these sub-agents as they tackle complex tasks. Monitor each agent as it works, and interrupt or inject context when needed.

Factory

11,781 Aufrufe • vor 6 Monaten