// Train & fine-tune
ARTv0.5.19
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!
Open source Maintained For developers
IN ONE PARAGRAPH
ART is 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!.
Good for: Developers and teams who want to train & fine-tune.
01How to start
- 1Read the official quick-start (link above).
- 2Install or sign up as the official guide describes.
- 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → unsloth Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. ★ 78k ms-swift Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025). ★ 16k LlamaFactory Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) ★ 76k xtuner A Next-Generation Training Engine Built for Ultra-Large MoE Models ★ 5.2k transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ★ 168k