Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonOpenPipe/ART

ART

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

89.9/100
9.0KForks: 764
View on GitHubHomepage →
Loading report...

Similar Projects

agent-lightning

82

The absolute trainer to light up AI agents.

Python15.4K

VLM-R1

55

Solve Visual Understanding with Reinforced VLMs

Python5.9K

EasyR1

78

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Python4.7K

AReaL

88

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Python4.6K
Back to List