用大模型自动优化可视化参数，让数据图表更准确、更易懂。
Explainable Iterative Data Visualisation Refinement via an LLM Agent
- 大模型将可视化评估转为语义任务，结合定量指标与定性分析
- 通过多轮迭代优化，自动生成高质量2D/3D数据图
- 适合需要快速生成可解释数据可视化的研究人员和分析师
高维数据的探索性分析依赖于将数据嵌入低维空间（通常为2D或3D），据此生成可视化图表以揭示有意义的结构并传达数据的几何与分布特征。然而，找到能真实反映底层数据现实并促进模式发现的算法配置（尤其是超参数设置）仍具挑战性。为此，我们提出一个基于大语言模型（LLM）的智能代理流程，将可视化评估与超参数优化视为语义任务。系统生成多维度报告，将硬性指标与描述性总结结合，并提供可操作的算法配置建议以优化可视化效果。通过实现该过程的迭代优化循环，系统能够全自动快速生成高质量可视化图表。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。