NVIDIA 的 NeMo 团队发布了 Molt，这是一个开源的智能体强化学习框架，旨在降低研究人员进行算法迭代的复杂性。代码库包含约 8.6K 行 RL 代码，显著小于 comparable frameworks like verl (62K lines) and slime (25K lines).

  • Molt 组合了 Ray 用于放置，vLLM 用于 rollout，以及 NVIDIA AutoModel with FSDP2 用于训练，无需 fork upstream components.
  • Agents are implemented as standard Python modules using either a Gymnasium-aligned Env or stock OpenAI/Anthropic SDKs via a loopback server.
  • The framework enforces three correctness invariants: token identity, policy-version semantics, and forward consistency, including rollout routing replay for mixture-of-experts models.
  • It supports scaling from dense 4B models to 700B MoE models and ships with Slurm scripts and prebuilt containers for deployment on H100/H200 hardware.

Molt aims to provide research infrastructure that allows researchers to hold the entire codebase in their head, facilitating easier modification of estimators and pipeline stages.