Agentic RL does not just sample text. It requires the model to act inside a real computer. Every rollout needs an isolated Linux environment with a filesystem, a network stack, and live processes.

Microsoft AI has released MAI-Cyber-1-Flash, its first model built specifically for cyber defense. The model does not ship as a standalone endpoint. It runs inside MDASH, Microsoft’s multi-model ...

In this tutorial, we build an advanced workflow around Anthropic’s financial-services repository and reproduce its skill-driven architecture in pure Python. We begin by installing the required ...

Perplexity has released pplx, an official command line client for its Search API. The tool returns grounded search results and extracted page text, all as JSON. According to its docs, it targets ...

The research frames a verifiable task as a triplet. It needs a precise task description, an executable repository environment, and a set of validation tests. A patch is correct only if it passes all ...

Open speech recognition stopped being a Whisper monoculture some time in the last twelve months. In March 2026 Cohere released Transcribe, a 2B Apache 2.0 model that ...

Two repositories were released. next-state/open-dreamer holds the training pipeline: a causal video tokenizer, an action-conditioned latent dynamics model, rollout ...

Architecturally, an orchestrator routes every request to one of three specialist sub-agents. Each sub-agent owns its own tools for reading or writing the memory store. First, the IngestAgent handles ...

Datalab has released Marker 2, a full rewrite of its open source document conversion pipeline. Marker converts PDF, image, PPTX, DOCX, XLSX, HTML, and EPUB files into markdown, JSON, HTML, or chunks.

Tokenization is the one part of the language modeling stack that almost nobody profiles. Gigatoken, released by Marcel Rød (a PhD student from Stanford) under an MIT license, argues that this was a ...

gpt-realtime-2.1-mini is a mini reasoning model for realtime voice interactions. It responds to audio and text inputs over a live connection. OpenAI positions it as the faster, more cost-efficient ...

Ant Group’s Robbyant has released LingBot-VLA 2.0, a Vision-Language-Action (VLA) foundation model for robots. The release includes a technical report, an Apache-2.0 codebase, and a 6B checkpoint. The ...