Explainable Iterative Data Visualisation Refinement via an LLM Agent

Computer Science > Human-Computer Interaction [Submitted on 2 Mar 2026] Explainable Iterative Data Visualisation Refinement via an LLM Agent Burak Susam, Tingting Mu 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. Subjects: Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) Cite as: arXiv:2604.15319 [cs.HC]   (or arXiv:2604.15319v1 [cs.HC] for this version)   https://doi.org/10.48550/arXiv.2604.15319 Focus to learn more Submission history From: Burak Susam [view email] [v1] Mon, 2 Mar 2026 17:51:04 UTC (1,426 KB) Access Paper: HTML (experimental) view license Current browse context: cs.HC < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)