Thanks to visit codestin.com
Credit goes to Github.com

Skip to content
forked from OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

License

Notifications You must be signed in to change notification settings

namanvirk18/ART

 
 

Repository files navigation

ART logo

Agent Reinforcement Trainer

Train multi-step agents for real-world tasks using GRPO

PRs Welcome PyPI Open in Colab Discord Documentation

Open-source RL framework that trains more reliable agents through experience-based learning with easy GRPO integration.

ART Demo

About

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 96.2%
  • Jupyter Notebook 3.2%
  • Shell 0.6%