Skip to main content

Get Started with AlphaApollo

Follow these steps to set up your environment and run your first agentic reasoning task.

Quick Start

Installation

bash
conda create -n alphaapollo python==3.12 -y
conda activate alphaapollo


git clone https://github.com/tmlr-group/AlphaApollo.git
cd AlphaApollo


bash installation.sh

Demo Programs

bash
# Method 1: workflow entrypoint
# no-tool reasoning
python3 -m alphaapollo.workflows.test \
  --model.path=Qwen/Qwen2.5-3B-Instruct \
  --preprocess.data_source=math-ai/aime24


# tool-integrated reasoning
python3 -m alphaapollo.workflows.test \
  --model.path=Qwen/Qwen2.5-3B-Instruct \
  --preprocess.data_source=math-ai/aime24 \
  --env.informal_math.enable_python_code=true \
  --env.informal_math.enable_local_rag=false \
  --env.max_steps=4


# Method 2: script entrypoint
bash examples/test/run_test_informal_math_no_tool.sh # no-tool reasoning
bash examples/test/run_test_informal_math.sh # tool-integrated reasoning

What's Next?

📚 Documentation

Explore the full documentation to learn about core modules, configurations, and advanced features.

Read Docs

🛠️ Built-in Tools

Learn how to use and extend built-in tools like the Python interpreter and local RAG module.

Explore Tools

🤝 Contribute

Join the community and help us improve AlphaApollo by contributing new algorithms or environments.

GitHub