GitHub 项目简介: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO.
README: ART is an open-source RL framework that improves agent reliability by allowing LLMs to **learn from experience**. ART provides an ergonomic harness for integrating GRPO into any p…
README: Train multi-step agents for real-world tasks using GRPO.
README: ART provides convenient wrappers for introducing RL training into **existing applications**. We abstract the training server into a modular service that your code doesn't need to…
README: **Train from anywhere.** Run the ART client on your laptop and let the ART server kick off an ephemeral GPU-enabled environment, or run on a local GPU.