Titan AI LogoTitan AI

ART

7,235
525
Python

Project Description

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!

Project Information

Created on 3/10/2025
Updated on 9/15/2025