🚨 New: Integrating Harbor (Harbor Framework) for end-to-end Computer-Use... evaluation(for Windows and Linux) at scale with Thinking Machines' Tinker, OSWorld, Daytona, and bare-metal servers. We just added support for Computer Use, Tinker, and OSWorld to Harbor - a framework for evaluating agents and generating RL training data by running large-scale rollouts across parallel sandboxed environments and collecting trajectories for SFT and RL. Repo and blogpost below 👇show more

Introducing agent-desktop agent-browser, for your whole computer → Computer... Use for any coding agent → macOS, Windows and Linux → Runs in bg while you keep working → Agents use your computer in parallel, each with its own cursorshow more

This is hugeeee for open-source RL environments. You can... now discover environments across OpenEnv, Verifiers, Harbor, NeMo Gym, and more, all on the Hugging Face Hub. A common home for RL environments is long overdue. Excited for what’s coming next !show more

Introducing autoresearch for arXiv papers: replicate and experiment on... any arXiv paper using an army of Claude/Codex agents For post-training, your agents can use Tinker to launch concurrent RL runs while you watch your experiment tree grow Try it out now on OpenResearch:show more

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

Introducing RL Environment Creator Skill Now any one can... create RL environments $ npx skills add adithya-s-k/RL_Envs_101 > You can create environments across multiple frameworks like OpenEnv, OpenReward, Verifiers, NemoGym ... > the repo has live working examples of environments that your coding agent can reference > The skill is design to first understand what type of model you are training and create an environment while keeping that in mind ps. There’s a lot more to building RL environments that can be used for training. One major aspect is the data, which this skill can’t directly solve. However, the skill will help with implementing tools, rewards, and other components of an RL environment, making it easier to go from idea to implementation quickly across different frameworks. Let me know if you’d be interested in a detailed, end-to-end blog/tutorial on building an environment and actually training a model for a useful use case.show more

GPT-6.1 Sol is here. Upgraded with stronger agentic coding... and computer use, near-Astra performance, and cached input at a 95% discount to standard input pricing. GPT-6.1 Sol is built for complex refactors, deep codebase investigations, and long-running agents across apps.show more

GPT-6 Astra test 4/n Prompt: "Implement pen spinning with... a dexterous hand. Use Isaac Lab for RL training, use the Sharpa hand, and create the pen mesh yourself. Give me a trained RL policy and a visualization video. You are free to search the web and download papers or anything else you need." After running autonomously for a day and a half (including training the policy), this is what we got: Credit: my student Chengyang Lishow more

Throughout my journey in developing multimodal models, I’ve always... wanted a framework that lets me plug & play modality encoders/decoders on top of an auto-regressive LLM. I want to prototype fast, try new architectures, and have my demo files scale effortlessly — with full support for parallelism and optimization. Not just to hack⚙️, but also to scale🚀. So finally we built it for ourselves. LMMs-Engine: a lean, efficient framework built to train unified multimodal model at scale. From Qwen LLM, VLM, LLaVA-OV, and WanVideo, to unified models like Qwen-Omni and BAGEL — plus Linear-Attn GDN and research prototypes like RAE and SiT - all under one modular system that seamlessly integrates diverse datasets and optimization strategies. Powered by FSDP2 multi-dim parallelism, Ulysses sequence parallel, Flash-Attention, Liger Kernels, and Native Sparse Attention (also with bonus support for the Muon optimizer for all models).show more

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: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reproducible, general environment focusing exclusively on the Windows operating system (OS) where agents can operate freely within a real Windows OS and use the same wide range of applications, tools, and web browsers available to human users when solving tasks. We adapt the OSWorld framework (Xie et al., 2024) to create 150+ diverse Windows tasks across representative domains that require agent abilities in planning, screen understanding, and tool usage. Our benchmark is scalable and can be seamlessly parallelized in Azure for a full benchmark evaluation in as little as 20 minutes. To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi. Our agent achieves a success rate of 19.5% in the Windows domain, compared to 74.5% performance of an unassisted human. Navi also demonstrates strong performance on another popular web-based benchmark, Mind2Web. We offer extensive quantitative and qualitative analysis of Navi's performance, and provide insights into the opportunities for future research in agent development and data generation using Windows Agent Arena.show more

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.show more

New research from Databricks: LLMs Can Learn to Reason... via Off-Policy RL Optimal Advantage-based Policy Optimization with Lagged Inference policy (OAPL) shows you don’t need strict on-policy training to improve reasoning. It matches or beats Group Relative Policy Optimization (GRPO), stays stable with large policy lag, and uses ~3× fewer training generations. For Databricks customers, it’s a simpler, practical, and equally powerful approach to RL that Databricks is pioneering internally — and bringing directly to Databricks customers, so enterprises can improve agents using the same methods we use for our in-house agents, without complex infrastructure changes.show more

Today, we released Lyra 2.0, a framework for generating... persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: 📄 Read the paper:show more

The ocean is a natural resource and treasure for... human beings and a blue harbor for marine life. Let's look at the beautiful sea life and listen to the sound of the sea. #sea #ocean #environment #seaprotectionshow more

What is the best video editing agent for short... form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!show more

1/ Today we're announcing the stable Cua Driver release... for Omarchy - a new foundation for computer use, built into the OS from the ground up. Over the last month, we worked directly with DHH, Spencer Bull and vaxry to bring a native synthetic cursor to Omarchy's Hyprland compositor, enabling true multi-cursor computer use at the OS level. Cua Driver is open source and available atshow more

🚨Current scalable RL algos train a policy w/o value... func, which is limiting with learning in open-ended, non-stationary, dynamic environments. But, how to scale value-based RL with more data/compute is unclear... Not anymore: presenting scaling laws for value-based RL 🧵⬇️show more

Collecting audio data in the real world. Live music,... real-world RL, good vibes across the city, and better tools made for musicians 🎵🌉show more

As a supporter of the open weights ecosystem, we're... proud to be a post-training partner for NVIDIA Nemotron. We post-train Nemotron models for customer use cases, de-risk mainline RL runs on our AC2 platform and training stack, and contribute aggregate workload statistics for inference benchmarking. This is how open models get better, and we're excited to keep working closely with NVIDIA AI.show more

Today, we're open sourcing the first computer-use dataset for... design. We captured 200+ hours and 3400+ trajectories of real design work in Figma, recording step by step how designers execute complex, long-horizon tasks. FigmaTrace dataset, paper, and blog below :) Patronus AIshow more