Large language models are increasingly used as open-ended search operators in evolutionary optimization. We introduce Evolutionary Feature Engineering (EFE), a framework for using LLM-based evolution to discover preprocessing transformations for structured data. EFE represents transformations as Python programs with a standardized fit/transform interface, allowing them to be inserted directly into existing machine learning pipelines. During evolution, candidate programs are refined using dataset context, summary statistics, and downstream performance feedback on validation set. We instantiate EFE in two settings. For time-series forecasting, EFE-Time learns invertible, dataset-specific normalizations that improve off-the-shelf time-series foundation models. It reduces forecasting errors (MASE, WQL, MAE) 3% or more when averaged across datasets and improvements are as much as 19% on the COVID-Deaths dataset. Notably, these improvements occur with recent TSFMs such as Chronos-2. For tabular prediction, EFE-Tab evolves compact feature programs that add useful interpretable features and remove redundant ones, improving or matching existing LLM-based feature-engineering methods. We found EFE-Tab to be particularly effective on classical decision trees, where small sets of evolved features yield competitive accuracy while preserving interpretability. Overall, EFE demonstrates that LLM-based evolution can improve both accuracy and interpretability when automatically tackling structured data.
Can Large Language Models Be Trusted as Evolutionary Optimizers for Network-Structured Combinatorial Problems?
Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University(数学科学系,物理与数学科学学院,南洋理工大学);School of Computer Science and Engineering, Nanyang Technological University(计算机科学与工程学院,南洋理工大学)
Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming
Dept. of Computer Science \& Information Systems, BITS Pilani, Goa, India School of Computer Science \& Engineering, University of New South Wales, Australia
From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge
Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR)(新加坡制造技术研究院,新加坡科技研究局);Advanced Remanufacturing and Technology Centre (ARTC), Agency for Science, Technology and Research (A*STAR)(先进再制造与技术中心,新加坡科技研究局);Nanyang Technological University(南洋理工大学)
Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection
International Centre for Theoretical Physics Asia-Pacific(国际理论物理中心亚太中心);University of Chinese Academy of Sciences(中国科学院大学);Taiji Laboratory for Gravitational Wave Universe(引力波宇宙Taiji实验室);Tsinghua University(清华大学)
Federated Learning for Clinical Structured Data: A Benchmark Comparison of Engineering and Statistical Approaches
Duke-NUS Medical School(杜克-新加坡国立大学医学院);Duke University(杜克大学);Institute of High Performance Computing, Agency for Science, Technology and Research(新加坡科技研究局高性能计算研究院);Singapore Health Services(新加坡保健服务集团);Singapore General Hospital(新加坡中央医院);Imperial College London(帝国理工学院);National University of Singapore(新加坡国立大学)