arXiv cs.AI· Burak Susam, Tingting Mu·· 10 小时前AI 评分29
基于 LLM Agent 的可解释迭代数据可视化优化
Explainable Iterative Data Visualization Refinement via an LLM Agent
AI 导读
研究提出一种 agentic AI 流水线，将可视化评估与超参数优化视为语义任务，结合严格定量评估与 LLM 对定性人类判断的近似，自动生成多维报告并给出算法配置建议。系统通过迭代优化循环全自动快速产出高质量可视化图，用于高维数据嵌入的低维可视化。
正文 · 原文
Abstract:Exploratory analysis of high-dimensional data relies on embedding the data into a low-dimensional space, based on which a visualization plot is produced to uncover meaningful structures and to communicate geometric and distributional data characteristics. Finding a suitable embedding algorithm configuration, particularly the hyperparameter setting, to produce a visualization plot that faithfully represents the underlying reality and encourages pattern discovery is labor-intensive and requires domain knowledge. To ease this burden, we propose an agentic AI pipeline that integrates rigorous quantitative assessment with large language model (LLM) based approximation of qualitative human judgment and insight. By treating visualization evaluation and hyperparameter optimization as a semantic task, our system generates a multi-faceted report that contextualizes quantitative metrics with descriptive summaries, and suggests actionable recommendations of algorithm configuration for refining data visualization. Through an iterative refinement loop, the system rapidly produces 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:2604.15319v3 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2604.15319 arXiv-issued DOI via DataCite |
Submission history
From: Burak Susam [view email]
[v1]
Mon, 2 Mar 2026 17:51:04 UTC (1,426 KB)
[v2]
Wed, 22 Apr 2026 16:15:41 UTC (1,426 KB)
[v3]
Tue, 10 Nov 2026 07:47:44 UTC (3,055 KB)
来源：arXiv cs.AI · arxiv.org