Hacker NewsART – a new open-source RL framework for training agents
https://github.com/OpenPipe/ART
#HackerNews #OpenSource #RLFramework #TrainingAgents #ReinforcementLearning #ART
GitHub - 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!
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! - OpenPipe/ART