# Exploring Agentic Approaches for Data Issue Detection and Repair in AI-Assisted Visualization

arXiv: https://arxiv.org/abs/2608.21602 · HTML: https://mlsanity.com/paper/2608.21602/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 13 of 13)

- [Towards Natural Language Interfaces for Data Visualization: A Survey](https://mlsanity.com/paper/2109.03506/) (2021)
- [Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks](https://mlsanity.com/paper/1804.03126/) (2018)
- [VisEval: A Benchmark for Data Visualization in the Era of Large Language Models](https://mlsanity.com/paper/2407.00981/) (2024)
- [WaitGPT: Monitoring and Steering Conversational LLM Agent in Data Analysis with On-the-Fly Code Visualization](https://mlsanity.com/paper/2408.01703/) (2024)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024)
- [How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?](https://mlsanity.com/paper/2407.17291/) (2024)
- [How Do Analysts Understand and Verify AI-Assisted Data Analyses?](https://mlsanity.com/paper/2309.10947/) (2023)
- [VizLinter: A Linter and Fixer Framework for Data Visualization](https://mlsanity.com/paper/2108.10299/) (2021)
- [Surfacing Visualization Mirages](https://mlsanity.com/paper/2001.02316/) (2020)
- [Dango: A Mixed-Initiative Data Wrangling System using Large Language Model](https://mlsanity.com/paper/2503.03154/) (2025)
- [BugDoc: Algorithms to Debug Computational Processes](https://mlsanity.com/paper/2004.06530/) (2020)
- [QFix: Diagnosing errors through query histories](https://mlsanity.com/paper/1601.07539/) (2016)

## Abstract (arXiv)

AI is increasingly lowering the barrier to data analysis and creating visualization scripts. However, a key obstacle in AI-assisted visualization is that certain data issues can lead to visualizations that are plausible, but misrepresent the underlying data. These textitvisualization defects are elusive and difficult to fix, particularly for non-experts who may not know what data issues cause them or how to guide AI systems to resolve them. We present findings of a preliminary empirical investigation of how commercial LLMs identify and repair defect-inducing data issues. Using a curated subset of the 911 emergency-call dataset with five injected data issues, we evaluated GPT-5, GPT-4o, GPT-4, and Claude Sonnet 4.6 under a three-stage prompting protocol, including zero-shot, guided issue-identification, and guided issue-repair. We executed this protocol under two conditions: single-agent and a multi-agent orchestration that separates data issue detection, review, repair planning, data repair, and repair quality assurance. We observed that across both conditions, LLMs identified and repaired single-field issues (e.g., missing values) but struggled to identify and repair temporal, geographic, and semantic issues. Based on these observations, we discuss design implications for agentic visualization systems, including explicit representation of data assumptions, selective human intervention for ambiguous decisions, and evidence-based repair.