PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback

TL;DR

PlotGen introduces a multi-agent LLM framework that automates scientific data visualization by iteratively refining plots through multimodal feedback, significantly improving accuracy and user trust.

Contribution

It presents a novel multi-agent system that orchestrates LLMs and multimodal feedback to automate and enhance scientific data visualization creation.

Findings

Achieves 4-6% improvement on MatPlotBench dataset.

Reduces debugging time for novice users.

Enhances trust in LLM-generated visualizations.

Abstract

Scientific data visualization is pivotal for transforming raw data into comprehensible visual representations, enabling pattern recognition, forecasting, and the presentation of data-driven insights. However, novice users often face difficulties due to the complexity of selecting appropriate tools and mastering visualization techniques. Large Language Models (LLMs) have recently demonstrated potential in assisting code generation, though they struggle with accuracy and require iterative debugging. In this paper, we propose PlotGen, a novel multi-agent framework aimed at automating the creation of precise scientific visualizations. PlotGen orchestrates multiple LLM-based agents, including a Query Planning Agent that breaks down complex user requests into executable steps, a Code Generation Agent that converts pseudocode into executable Python code, and three retrieval feedback agents - a Numeric Feedback Agent, a Lexical Feedback Agent, and a Visual Feedback Agent - that leverage multimodal LLMs to iteratively refine the data accuracy, textual labels, and visual correctness of generated plots via self-reflection. Extensive experiments show that PlotGen outperforms strong baselines, achieving a 4-6 percent improvement on the MatPlotBench dataset, leading to enhanced user trust in LLM-generated visualizations and improved novice productivity due to a reduction in debugging time needed for plot errors.