OpenPipe / ARTLinks

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, Kimi, and more!
1,108Updated this week

Alternatives and similar repositories for ART

Users that are interested in ART are comparing it to the libraries listed below

Sorting: