AReaL
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
What is AReaL?
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Overview of AReaL
What it is
AReaL is a reinforcement learning (RL) infrastructure designed to bridge foundation model training with modern agent-based applications. It was originally developed by researchers and engineers from Tsinghua IIIS and the AReaL Team at Ant Group. Built on a fully asynchronous RL training paradigm, AReaL is optimized for efficiency and scalability, making it particularly well-suited for training large-scale reasoning and agentic models.
Key features
- Flexibility: Seamless customization for agentic RL and online RL training for black-box agent applications by simply replacing the
base_url. - Scalability: Stable fully asynchronous RL training with industry-leading speed.
- Cutting-Edge Performance: State-of-the-art math, coding, search, and customer service agents.
Use cases
AReaL is used for training large-scale reasoning and agentic models. Example tasks include math reasoning (e.g., GSM8K), multi-turn math agent, countdown numbers game, search agent (ASearcher), and customer service agent. It supports end-to-end asynchronous RL training for agentic applications.
Getting started
git clone https://github.com/areal-project/AReaL
cd AReaL
pip install uv
### Install flash-attn pre-built wheel first to avoid compiling from source
### (pick the wheel matching your Python version; see https://github.com/mjun0812/flash-attention-prebuild-wheels/releases)
uv pip install "https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.16/flash_attn-2.8.3+cu128torch2.9-cp312-cp312-linux_x86_64.whl"
uv sync --extra cuda # installs training packages + SGLang (default inference backend)
### For vLLM instead: cp pyproject.vllm.toml pyproject.toml && cp uv.vllm.lock uv.lock && uv sync --extra cuda
To run on a single node:
python3 examples/math/gsm8k_rl.py --config examples/math/gsm8k_grpo.yaml scheduler.type=local
For comprehensive setup instructions, see the repository README.
License and pricing
License: Apache-2.0. Pricing: open source (free).
Based on the project's public README and repository metadata.