Towards Automated Causal Effect Estimators through Self-Evolving AI
Explore how the best program evolves across checkpoints. Select a run, then click checkpoints to see code changes.
Evolution trajectories showing best-so-far combined score across iterations. Select experimental conditions to filter.
Three independent LLM judges assess each evolved estimator for novelty, similarity to known methods, and complexity.
How evolved estimators compare against classical baselines (BART, Causal Forest, Backdoor adjustment).
| Dataset | Metric | Best Evolved | Baseline | Win Rate | Best Improvement |
|---|
Get started with running your own causal inference evolution experiments.
# Clone the repository
git clone https://github.com/yiqunchen/causal-agent.git
cd causal-agent
# Install dependencies (requires uv)
uv sync
# Configure API keys
export OPENAI_API_KEY="..."
export GOOGLE_API_KEY="..."
# Run an evolution experiment
uv run python main.py \
--dataset ihdp \
--model gpt-5 \
--lambda-weight 0.2 \
--max-iterations 100 \
--train-test-split 50:50