Explainable Iterative Data Visualisation Refinement via an LLM Agent

ArXi:2604.15319v1 Announce Type: cross Exploratory analysis of high-dimensional data relies on embedding the data into a low-dimensional space (typically 2D or 3D), based on which visualization plot is produced to uncover meaningful structures and to communicate geometric and distributional data characteristics. However, finding a suitable algorithm configuration, particularly hyperparameter setting, to produce a visualization plot that faithfully represents the underlying reality and encourages pattern discovery remains challenging.