Explainable Iterative Data Visualisation Refinement via an LLM Agent

• URL: http://arxiv.org/abs/2604.15319v2
• Date: Wed, 22 Apr 2026 16:15:41 GMT
• Title: Explainable Iterative Data Visualisation Refinement via an LLM Agent
• Abstract summary: We propose an agentic AI pipleline to bridge the gap between rigorous quantitative assessment and qualitative human insight.<n>Our system generates a multi-faceted report that contextualizes hard metrics with descriptive summaries.<n>It is able to produce rapidly a high-quality visualization plot, in full automation.
• Score: 7.143367458097555
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs [81.43302841109349]
  Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs)<n>We propose an automated multi-agent framework to reconstruct the evolutionary graph of dataset development.
  arXiv  Detail & Related papers  (2026-04-12T06:24:07Z)
• MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval [111.99106496142474]
  Visual Document Retrieval (VDR) requires representations that capture both fine-grained visual details and global document structure.<n>Existing VDR models struggle to balance effectiveness and efficiency when processing high-resolution documents.<n>We propose a new X-VisEmb paradigm that progresses from multi-resolution sampling and encoding, through cross-granularity feature fusion, to adaptive representation distillation.
  arXiv  Detail & Related papers  (2026-03-07T15:17:22Z)
• o-MEGA: Optimized Methods for Explanation Generation and Analysis [1.4113638641649384]
  textbftexttto-mega is a tool designed to automatically identify the most effective explainable AI methods.<n>We demonstrate improved transparency in automated fact-checking systems.
  arXiv  Detail & Related papers  (2025-09-30T21:08:36Z)
• Spatial Understanding from Videos: Structured Prompts Meet Simulation Data [89.77871049500546]
  We present a unified framework for enhancing 3D spatial reasoning in pre-trained vision-language models without modifying their architecture.<n>This framework combines SpatialMind, a structured prompting strategy that decomposes complex scenes and questions into interpretable reasoning steps, with ScanForgeQA, a scalable question-answering dataset built from diverse 3D simulation scenes.
  arXiv  Detail & Related papers  (2025-06-04T07:36:33Z)
• An Incremental Non-Linear Manifold Approximation Method [0.0]
  This research develops an incremental non-linear dimension reduction method using the Geometric Multi-Resolution Analysis (GMRA) framework for streaming data.<n>The proposed method enables real-time data analysis and visualization by incrementally updating the cluster map, basis PCA vectors, and wavelet coefficients.
  arXiv  Detail & Related papers  (2025-04-12T03:54:05Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Noisy Data Visualization using Functional Data Analysis [14.255424476694946]
  We propose a new data visualization method called Functional Information Geometry (FIG) for dynamical processes. We experimentally demonstrate that the resulting method outperforms a variant of EIG designed for visualization. We then use our method to visualize EEG brain measurements of sleep activity.
  arXiv  Detail & Related papers  (2024-06-05T15:53:25Z)
• ShaRP: Shape-Regularized Multidimensional Projections [71.30697308446064]
  We present a novel projection technique - ShaRP - that provides users explicit control over the visual signature of the created scatterplot. ShaRP scales well with dimensionality and dataset size, and generically handles any quantitative dataset.
  arXiv  Detail & Related papers  (2023-06-01T11:16:58Z)
• Information-Theoretic Odometry Learning [83.36195426897768]
  We propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language.
  arXiv  Detail & Related papers  (2022-03-11T02:37:35Z)
• Scalable semi-supervised dimensionality reduction with GPU-accelerated EmbedSOM [0.0]
  BlosSOM is a high-performance semi-supervised dimensionality reduction software for interactive user-steerable visualization of high-dimensional datasets. We show the application of BlosSOM on realistic datasets, where it helps to produce high-quality visualizations that incorporate user-specified layout and focus on certain features.
  arXiv  Detail & Related papers  (2022-01-03T15:06:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.