Explainable Iterative Data Visualisation Refinement via an LLM Agent

TL;DR

This paper introduces an AI system that uses a large language model to iteratively refine data visualizations by combining quantitative metrics with human-like qualitative insights, automating the hyperparameter tuning process.

Contribution

It presents a novel agentic AI pipeline that treats visualization evaluation and hyperparameter optimization as semantic tasks, enabling automated, high-quality visualization refinement.

Findings

System generates multi-faceted reports with metrics and summaries.

Iterative optimization produces high-quality visualizations rapidly.

Automates hyperparameter tuning for data visualization.

Abstract

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. To address this challenge, we propose an agentic AI pipleline that leverages a large language model (LLM) to bridge the gap between rigorous quantitative assessment and qualitative human insight. By treating visualization evaluation and hyperparameter optimization as a semantic task, our system generates a multi-faceted report that contextualizes hard metrics with descriptive summaries, and suggests actionable recommendation of algorithm configuration for refining data visualization. By implementing an iterative optimization loop of this process, the system is able to produce rapidly a high-quality visualization plot, in full automation.