AI RESEARCH
Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation
arXiv CS.AI
•
ArXi:2603.09987v1 Announce Type: cross Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the large space of feature-operator combinations. Existing solutions rely on discrete search or latent generation, but they are frequently limited by sample inefficiency, invalid candidates, and redundant generations with limited coverage.