Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.15319 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910157336739840 |
|---|---|
| author | Susam, Burak Mu, Tingting |
| author_facet | Susam, Burak Mu, Tingting |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15319 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Explainable Iterative Data Visualisation Refinement via an LLM Agent Susam, Burak Mu, Tingting Human-Computer Interaction Artificial Intelligence 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. |
| title | Explainable Iterative Data Visualisation Refinement via an LLM Agent |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2604.15319 |