Meituan has released LongCat-2.0, a 1.6 trillion-parameter Mixture-of-Experts model that activates about 48 billion parameters per token. It pairs a native 1-million-token context, built on LongCat Sparse Attention, with training and serving run end-to-end on domestic AI ASIC superpods. Here is the architecture, the vendor-reported benchmarks, the API access path, and what remains unverified.

The post Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention appeared first on MarkTechPost.

We build an end-to-end GRPO training workflow that teaches Gemma-3 to reason through GSM8K math problems. We prepare the environment, authenticate with Hugging Face, load Gemma-3, and wrap examples into a reasoning-plus-answer prompt format. We define reward functions for format adherence and numeric correctness, then attach LoRA adapters to keep training lightweight. We evaluate a baseline, run GRPO to improve the policy through group-sampled generations, and optionally export the merged model.

The post Training Gemma-3 for Structured Mathematical Reasoning with Tunix GRPO, LoRA Adapters, and GSM8K Rewards appeared first on MarkTechPost.

Synthetic Sciences has released OpenScience, an Apache-2.0 AI workbench for scientific research. It works with any frontier or open-weight model, using your own API keys. It runs the full loop across machine learning, biology, physics, and chemistry. It ships 250+ editable skills and queryable scientific databases, and it runs on your own infrastructure.

The post Synthetic Sciences Releases OpenScience: An Open-Source, Model-Agnostic AI Workbench for Machine Learning, Biology, Physics, and Chemistry Research appeared first on MarkTechPost.

Sakana AI has added Sakana Translate to Sakana Chat. It runs on the Namazu model series. The tool translates bidirectionally across Japanese, English, and Chinese. Three modes ship together: Translate, Proofread, and Ask. This article breaks down each mode, the XCOMET-XL benchmark, and practical use cases.

The post Sakana AI Launches Sakana Translate, a Namazu-Powered Japanese–English–Chinese Translation Tool With Translate, Proofread, and Ask Modes appeared first on MarkTechPost.

Junyang Lin, the former technical lead of Alibaba’s Qwen, walked through the model family in a talk “towards a generalist model / agent,” then expanded it in an essay. We read both for practitioners: Qwen3 hybrid thinking modes and dynamic thinking budgets, where the merge fell short, the shift from reasoning thinking to agentic thinking, why agentic RL infrastructure is harder, and where reward hacking bites.

The post Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents appeared first on MarkTechPost.

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 […]

The post Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026 appeared first on MarkTechPost.

LlamaIndex’s legal-kb is a public reference app that gives agents filesystem-style access to a document knowledge base on Index v2. It exposes retrieve (hybrid semantic search), find, read, and grep as tools, with automatic per-file versioning and visual citations. The stack is TanStack Start, AI SDK 6 (ToolLoopAgent), Prisma, and WorkOS.

The post LlamaIndex ‘legal-kb’: Agentic Retrieval over Index v2 with retrieve, find, read, and grep Tools appeared first on MarkTechPost.

A hands-free NVIDIA agent framework hosts each RTL problem as a versioned repository, reaching 100% completion across benchmarks.

The post NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion appeared first on MarkTechPost.

Anthropic released Claude Science in beta on June 30, 2026. The app runs on existing Claude models. A coordinating agent delegates to domain specialists, a reviewer agent flags and corrects citations and numbers, and every figure ships with its exact code, environment, and full message history. It manages compute across local machines, HPC over SSH, and Modal, and connects to 60+ databases plus NVIDIA BioNeMo skills.

The post Anthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines appeared first on MarkTechPost.

In this tutorial, we build an end-to-end accounts-payable extraction pipeline with lift-pdf, using synthetic invoice PDFs as controlled test documents and a structured JSON schema as the target output format. Instead of treating invoice parsing as a simple OCR task, we frame it as schema-guided document understanding: we generate realistic invoices, define fields such as […]

The post Designing a Schema-Guided Invoice Intelligence Pipeline with lift-pdf for Accounts-Payable Extraction, Validation, and Ledger Generation appeared first on MarkTechPost.

Mistral AI released Leanstral 1.5, a free Apache-2.0 code agent model for Lean 4. It saturates miniF2F and solves 587 of 672 PutnamBench problems. The 119B mixture-of-experts activates 6.5B parameters per token. We break down its architecture, benchmarks, real bug-finding case studies, and deployment code.

The post Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems appeared first on MarkTechPost.

NVIDIA’s ASPIRE writes and refines robot control programs, then distills validated repairs into a reusable skill library. It gains up to 77 points on LIBERO-Pro and transfers zero-shot to unseen long-horizon tasks.

The post NVIDIA AI Introduces ASPIRE: A Self-Improving Robotics Framework Reaching 31% Zero-Shot on LIBERO-Pro Long Tasks appeared first on MarkTechPost.

WebBrain is a free, MIT-licensed AI browser agent for Chrome and Firefox. It reads pages, extracts data, and automates multi-step tasks through Ask and Act modes. Run it on local models like llama.cpp or Ollama for privacy, or connect any cloud API.

The post Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox appeared first on MarkTechPost.