Problem
Research questions and friction points this paper is trying to address.
causal inference
causal effect estimation
method selection
real-world data complexity
statistical methodology
InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI
🤖 AI Summary
Causal effect estimation remains highly challenging due to data complexity and sensitivity to model assumptions. This work proposes InferenceEvolve, a novel framework that, for the first time, integrates large language models with evolutionary algorithms to automatically discover high-performance causal estimators tailored to observed data mechanisms. By employing a surrogate objective function to guide program self-evolution, the method operates without requiring semi-synthetic data. Evaluated on standard benchmarks, InferenceEvolve outperforms existing approaches, with its Pareto-optimal solutions dominating both evaluation metrics among 58 submissions in a community competition. The framework substantially advances the automation and robustness of causal inference.
📝 Abstract
Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in accelerating scientific discovery, we introduce InferenceEvolve, an evolutionary framework that uses large language models to discover and iteratively refine causal methods. Across widely used benchmarks, InferenceEvolve yields estimators that consistently outperform established baselines: against 58 human submissions in a recent community competition, our best evolved estimator lay on the Pareto frontier across two evaluation metrics. We also developed robust proxy objectives for settings without semi-synthetic outcomes, with competitive results. Analysis of the evolutionary trajectories shows that agents progressively discover sophisticated strategies tailored to unrevealed data-generating mechanisms. These findings suggest that language-model-guided evolution can optimize structured scientific programs such as causal inference, even when outcomes are only partially observed.
Innovation
Methods, ideas, or system contributions that make the work stand out.
causal inference
large language models
evolutionary framework
automated method discovery
proxy objectives
🔎 Similar Papers
No similar papers found.
