ART
a new open-source RL framework for training agents. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more! ART is a new open-source framework for training agents using reinforcement learning (RL).
LibraryOpen source
Reactions (1)
Similar products
by description similarity
SkillGraph
github.comOpen-source agentic framework with skills instead of tools
Next-Gen AI Training
github.comLLM-RLHF-Tuning with PPO and DPO
RL-training an AI agent to RL-train AI agents.
RULER
openpipe.aiEasily apply RL to any agent
Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.