用AI自进化生成更优因果推断方法，效果超越人类专家。
InferenceEvolve: Towards Automated Causal Effect Estimators through Self-Evolving AI
- 用大语言模型迭代演化因果推断算法
- 在竞赛中击败58个参赛人类方案，性能达帕累托前沿
- 适合需自动化因果分析的研究者
因果推断是科学发现的核心，但方法选择因统计复杂性与真实数据挑战而困难。受人工智能加速科学发现的启发，我们提出InferenceEvolve，一种基于大语言模型的演化框架，用于发现并迭代优化因果推断方法。在多个常用基准上，InferenceEvolve生成的估计器持续优于现有基线：在最近一场社区竞赛中，其最优演化估计器在两个评估指标上均位于帕累托前沿，超越58项人类提交方案。我们还设计了无半合成结果场景下的稳健代理目标，取得有竞争力的结果。对演化轨迹的分析显示，智能体逐步发现针对未公开数据生成机制的复杂策略。这些结果表明，语言模型引导的演化可优化结构化科学程序（如因果推断），即使结果仅部分可观测。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。