Agentic reinforcement learning (RL) extends traditional LLM training by optimizing not just a single-turn response, but an entire decision-making process learned through direct interaction with an environment during training. Unlike traditional single-turn reinforcement learning or offline preference-based methods that rely on static datasets, agentic RL trains policies by actively collecting on-policy data as the agent plans actions, invokes tools, observes outcomes, and adapts its behavior over multi-step trajectories in either simulated or real environments. This interaction-driven optimization assigns credit across […]

Arabic is one of the most widely spoken languages in the world, with hundreds of millions of speakers across more than twenty countries. Despite this global reach, Arabic is not a monolithic language. Modern Standard Arabic coexists with a rich landscape of regional dialects that differ significantly in vocabulary, syntax, phonology, and cultural grounding. These dialects are the primary medium of daily communication, oral storytelling, poetry, and social interaction. However, most existing benchmarks for Arabic large language models focus almost […]

This is the second blog in a three-part series on China’s open source community’s historical advancements since January 2025’s “DeepSeek Moment.” The first blog is available here, and the third blog is available here. In    

The best thing about agent skills is upskilling your agents on hard problems. There are two ways to look at that: You can take Opus 4.5 or other SOTA models and tackle the hardest problems out there. You can take models that run on your laptop and upskill them to harder problems. In this blog post, we’ll show you how to take on the latter. This blog post walks through the process of using a new tool, upskill, to generate […]

TL;DR: Daggr is a new, open-source Python library for building AI workflows that connect Gradio apps, ML models, and custom functions. It automatically generates a visual canvas where you can inspect intermediate outputs, rerun individual steps, and manage state for complex pipelines, all in a few lines of Python code! Table of Contents Background Getting Started Sharing Your Workflows End-to-End Example with Different Nodes Next Steps    

Welcome back! This is the second part of our series on training efficient text-to-image models from scratch. In the first post of this series, we introduced our goal: training a competitive text-to-image foundation model entirely from scratch, in the open, and at scale. We focused primarily on architectural choices and motivated the core design decisions behind our model PRX. We also released an early, small (1.2B parameters) version of the model as a preview of what we are building (go […]

This is the third and final blog in a three-part series on China’s open source community’s historical advancements since January 2025’s “DeepSeek Moment.” The first blog on strategic changes and open artifact growth is available here,    

Two months since releasing our first batch of Holo2 models, H Company is back with our largest UI localization model yet: Holo2-235B-A22B Preview. This model achieves a new State-of-the-Art (SOTA) record of 78.5% on Screenspot-Pro and 79.0% on OSWorld G. Available on Hugging Face, Holo2-235B-A22B Preview is a research release focused on UI element localization. Agentic Localization High-resolution 4K interfaces are challenging for localization models. Small UI elements can be difficult to pinpoint on a large display. With agentic localization, […]

TL;DR: Benchmark datasets on Hugging Face can now host leaderboards. Models store their own eval scores. Everything links together. The community can submit results via PR. Verified badges prove that the results can be reproduced. Evaluation is broken Let’s be real about where we are with evals in 2026. MMLU is saturated above 91%. GSM8K hit 94%+. HumanEval is conquered. Yet some models that ace benchmarks still can’t reliably browse the web, write    

SyGra 2.0.0 introduces Studio, an interactive environment that turns synthetic data generation into a transparent, visual craft. Instead of juggling YAML files and terminals, you compose flows directly on the canvas, preview datasets before committing, tune prompts with inline variable hints, and watch executions stream live—all from a single pane. Under the hood it’s the same platform, so everything you do visually generates the corresponding SyGra compatible graph config and task executor scripts. What Studio lets you do