In this tutorial, we build an end-to-end GRPO training workflow that teaches Gemma-3 to reason through GSM8K math problems using Tunix, JAX, LoRA, and custom reward functions. We start by preparing the environment, authenticating with Hugging Face, loading the Gemma-3 model, and wrapping GSM8K examples into a prompt format that requires both structured reasoning and […]
Meituan has released LongCat-2.0, a large-scale Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters and activates about 48 billion per token. The model targets agentic coding: code understanding, generation, and execution inside agent workflows. Two facts stand out. First, LongCat-2.0 supports a native 1-million-token context window. Second, both training and serving ran entirely
LlamaIndex has published legal-kb, a public reference application on GitHub. It is described as a knowledge base for legal documents, powered by LlamaIndex Index v2 (the LlamaParse Platform). The project demonstrates a pattern the team calls a Retrieval Harness for agentic retrieval. The approach differs from single-shot retrieval. Instead of one embedding search per query,
Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents cannot use that data until it becomes structured JSON. Open-source document extraction has become the standard way to do that conversion on your own hardware. Two different problems hide under the phrase ‘PDF to JSON.’ The first is schema-driven
Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026 Read More »
Junyang Lin was the technical lead of Alibaba’s Qwen project. He announced he was stepping down on March 3, 2026. He now lists himself as an independent researcher on his personal site. In a talk titled ‘Qwen: Towards a Generalist Model / Agent,‘ he walks through the Qwen family. It ends on a single line:
Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents Read More »
Imagine if you could bring 250 people together in a massive room and have them discuss and debate an important issue, arguing the points and counterpoints, and converging on answers that accurately reflect their collective knowledge, wisdom, values, and sensibilities. Now imagine that you convened this debate on America’s 250th birthday and asked 250 randomly
How America’s 250th birthday became a test of AI-powered collective intelligence Read More »
This week, Anthropic released Claude Science. It is an app for scientists, available in beta. It runs on Anthropic’s existing Claude models, not a new model. The app targets researchers who juggle databases, notebooks, and cluster terminals. It runs multi-step research and records how each result was made. The beta is available for Pro, Max,
NVIDIA Research introduced HORIZON, a hands-free agent framework for hardware design. It treats hardware design as repository-level code evolution. This research team exercises the register-transfer level (RTL) instantiation. A structured Markdown harness becomes a project pack. A self-contained agent loop then evolves an isolated git worktree. It commits a version only when an executable acceptance
Traditional robot programming is hard to scale. It requires orchestrating multimodal perception, physical contact dynamics, diverse configurations, and execution failures by hand. Code-as-policy systems let language models compose these into executable robot programs. That makes robot behavior inspectable, editable, and debuggable. But existing robotic coding agents run in naive execution environments. They receive only coarse,
Today, Mistral AI released Leanstral 1.5. It is a code agent model built for Lean 4. The release targets automated theorem proving and proof engineering. Weights are open under Apache 2.0. A free API endpoint, leanstral-1-5, is now live. Leanstral 1.5 updates the earlier Leanstral-2603 model. It belongs to the Mistral Small 4 family. What