NVIDIA has launched Molt, a PyTorch‑native framework for agentic reinforcement learning that emphasizes a compact codebase of roughly 8.6K lines of RL code. It integrates a single training backend (NeMo AutoModel) and serving engine (vLLM) with three modular components orchestrated through an asynchronous loop powered by Ray for placement. This design aims to provide a lightweight yet scalable solution for developing and deploying RL agents.