Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO.
[![PRs-Welcome][contribute-image]][contribute-url]
[][pypi-url]
## 🚀 W&B Training: Serverless RL
**W&B Training (Serverless RL)** is the first publicly available service for flexibly training models with reinforcement learning. It manages your training and inference infrastructure automatically, letting you focus on defining your data, environment and reward function—leading to faster feedback cycles, lower costs, and far less DevOps.
✨ **Key Benefits:**
- **40% lower cost** - Multiplexing on shared production-grade inference cluster
- **28% faster training** - Scale to 2000+ concurrent requests across many GPUs
- **Zero infra headaches** - Fully managed infrastructure that stays healthy
- **Instant deployment** - Every checkpoint instantly available via W&B Inference
```python
# Before: Hours of GPU setup and infra management
# RuntimeError: CUDA error: out of memory 😢
# After: Serverless RL with instant feedback
from art.serverless.backend import ServerlessBackend
model = art.TrainableModel(
project="voice-agent",
name="agent-001",
base_model="Qwen/Qwen3.6-27B"
)
backend = ServerlessBackend(
api_key="your_wandb_api_key"
)
model.register(backend)
# Edit and iterate in minutes, not hours!
```
[📖 Learn more about W&B Training →](https://docs.wandb.ai/guides/training)
## ART Overview
ART is an open-source RL framework that improves agent reliability by allowing LLMs to **learn from experience**. ART provides an ergonomic harness for integrating GRPO into any python application. For a quick hands-on introduction, run one of the notebooks below. When you're ready to learn more, check out the [docs](https://art.openpipe.ai).
## 📒 Notebooks
| Agent Task | Example Notebook | Description | Comparative Performance |
| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **ART•E [Serverless]** | [🏋️ Train agent](https://colab.research.google.com/github/openpipe/art-notebooks/blob/main/examples/art-e.ipynb) | Qwen 3.6 27B learns to search emails using RULER | 
[benchmarks](/dev/art-e/art_e/evaluate/display_benchmarks.ipynb) |
| **2048 [Serverless]** | [🏋️ Train agent](https://colab.research.google.com/github/openpipe/art-notebooks/blob/main/examples/2048/2048.ipynb) | Qwen 3.6 27B learns to play 2048 | 
[benchmarks](/examples/2048/display_benchmarks.ipynb) |
| **ART•E LangGraph** | [🏋️ Train agent](https://colab.research.google.com/github/openpipe/art-notebooks/blob/main/examples/langgraph/art-e-langgraph.ipynb) | Qwen 2.5 7B learns to search emails using LangGraph | [Link coming s
```
---
**Machine-readable endpoints**
- JSON: [`/api/graphcanon/tools/openpipe-art`](/api/graphcanon/tools/openpipe-art)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)
_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_