InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI
Can Wang, Hongyu Zhao, Yiqun Chen

TL;DR
InferenceEvolve leverages large language models in an evolutionary framework to automatically discover and refine causal inference methods, outperforming existing baselines on standard benchmarks.
Contribution
The paper introduces a novel AI-driven evolutionary approach for developing causal estimators, demonstrating superior performance and adaptability over traditional methods.
Findings
Best evolved estimator on benchmarks outperforms 58 human submissions.
Agents discover sophisticated, tailored strategies through evolutionary trajectories.
Proxy objectives enable effective causal inference without semi-synthetic outcomes.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
