Explainable Iterative Data Visualisation Refinement via an LLM Agent

Burak Susam; Tingting Mu

cs.HCMar 2, 2026

Explainable Iterative Data Visualisation Refinement via an LLM Agent

Authors: Burak Susam, Tingting Mu

Organizations: Department of Computer Science, University of Manchester, Manchester, M13 9PT, UK

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.

Figures & tables

Metric	Measures	Ideal	Aspect
\colrule $\rho_{s}$	Rank consistency	High ( $\uparrow$ )	Global order
$S$	Metric distortion	Low ( $\downarrow$ )	Global geom.
$R$	Scaling exp/comp	$\approx 1$	Global scale
$T(k)$	False neighbors	High ( $\uparrow$ )	Local prec.
$C(k)$	True neighbors	High ( $\uparrow$ )	Local recall
\botrule

Table 1: Summary of evaluation metrics and their interpretation.

Figure 1: Overview of the Agentic Visualization Refinement Pipeline. The system iteratively optimizes dimensionality reduction hyperparameters. Raw data is fed into the DR & Visualization Engine to create 2D embeddings and scatter plots. The Quantitative Analyst and Clustering Engines extract metrics using these embeddings and raw data. These metrics and hierarchy dendrograms, alongside the plots, are combined into an Instruction Prompt for the LLM Agent. The agent evaluates the current state of the visualization and outputs a JSON response containing hyperparameter recommendations, which are fed back into the DR and Visualization Engine for the next iteration until the best visualization is achieved. The convergence is determined using the quality score from the LLM agent or explicit score whose weights defined by the agent.

Panel of Figure 2 — Figure 2: LLM agent (GPT 5.2) response and corresponding visual areas on cell type clustering: (a) High-Dimensional PCA dendrogram, (b) Low-Dimensional t-SNE dendrogram, and (c) the resulting t-SNE embedding on Healthy Human Kidney scRNA-seq Dataset [ 18 ] with Initial t-SNE Hyperparameter Setting

		GPT-5.2		Gemini-3-Pro-Preview		Claude-Opus-4.5
Dataset	DR Method	Implicit	Explicit	Implicit	Explicit	Implicit	Explicit
Healthy Human Kidney (Sex-Based Profiling)	UMAP	7.60 $\rightarrow$ 8.90	8.15 $\rightarrow$ 8.47	7.50 $\rightarrow$ 8.50	8.31 $\rightarrow$ 8.29	7.20 $\rightarrow$ 7.20	8.23 $\rightarrow$ 8.28
	t-SNE	6.80 $\rightarrow$ 8.90	6.80 $\rightarrow$ 8.50	6.00 $\rightarrow$ 7.50	7.02 $\rightarrow$ 8.27	5.50 $\rightarrow$ 7.20	7.06 $\rightarrow$ 8.22
	PaCMAP	8.30 $\rightarrow$ 9.00	8.40 $\rightarrow$ 8.57	8.50 $\rightarrow$ 8.80	8.53 $\rightarrow$ 8.78	7.50 $\rightarrow$ 7.50	8.52 $\rightarrow$ 8.65
Mature Human Kidney (Immune Zonation)	UMAP	6.60 $\rightarrow$ 7.60	6.83 $\rightarrow$ 6.79	6.50 $\rightarrow$ 8.50	7.08 $\rightarrow$ 7.74	5.50 $\rightarrow$ 6.50	7.08 $\rightarrow$ 7.45
	t-SNE	6.00 $\rightarrow$ 7.60	6.98 $\rightarrow$ 8.49	7.50 $\rightarrow$ 7.90	7.63 $\rightarrow$ 7.79	6.50 $\rightarrow$ 6.50	7.37 $\rightarrow$ 7.41

Table 2: Comparison of Final Optimization Performance Across LLM Agents, DR Methods, and Scoring Mechanisms

Panel of Figure 3 — Figure 3: LLM agent (GPT 5.2) response and corresponding visual areas on cell type clustering: (a) High-Dimensional PCA dendrogram, (b) Low-Dimensional t-SNE dendrogram, and (c) the resulting t-SNE embedding on Healthy Human Kidney scRNA-seq Dataset [ 18 ] with Agent Optimized t-SNE Hyperparameter Setting

Panel of Figure 4 — Figure 4: Comparison of optimization trajectories across LLM agents. Each plot illustrates the overlapping implicit and explicit score progressions alongside corresponding quantitative metrics over successive pipeline iterations.

Data Visualization

Data visualization studies how visual representations help people explore, interpret, communicate, and reason about data.

See all 120 papers

InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization
Sep 6, 2026Hanya Sun, Chen Zhang, Sheng Liang +2Data Visualization LLM Prompting
Huawei Technologies Co., Ltd.
ChartDesign: Towards LLM Designer of Data Visualization
Apr 6, 2026Mohammed Afaan Ansari, Aniruddh Bansal, Tianyi ZhouData Visualization
University of Maryland, College Park College Park, MD, USA
De-rendering, Reasoning, and Repairing Charts with Vision-Language Models
Feb 23, 2026Valentin Bonas, Martin Sinnona, Viviana Siless +1Data Visualization Chart Understanding
Universidad Torcuato Di Tella, Buenos Aires, Buenos Aires, Argentina · Facultad de Ciencias Exactas y Naturales Universidad de Buenos Aires, Buenos Aires, Argentina · Consejo Nacional de Investigaciones Científicas y Técnicas, Buenos Aires, Argentina

Sep 6, 2026J/K move · Enter open · S save

InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization

Hanya Sun, Chen Zhang, Sheng Liang, Yongyue Zhang+1

Huawei Technologies Co., Ltd.

Data Visualization LLM Prompting Visual Analytics Automatic Prompt Optimization

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-stage visualization prompting pipeline (Explore--Focus--Test--Present) that emulates expert analytical workflows, together with VG-COPRO, a vision-guided automatic prompt optimization (APO) method adapted to jointly optimize such multi-stage, executable pipelines. To address the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. We assess IPM through a 100-chain human pilot and an expanded 300-chain agent-based evaluation spanning all ten domains. Experiments on public datasets show that InsightChain consistently outperforms competing prompting baselines. Existing APO methods fail to yield consistent gains on this multi-stage task, whereas VG-COPRO improves performance in both in-domain and cross-domain settings.

Abstract

Data Visualization

Explore similar work

InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization

ChartDesign: Towards LLM Designer of Data Visualization

De-rendering, Reasoning, and Repairing Charts with Vision-Language Models