Data-to-Dashboard: Multi-Agent LLM Framework for Insightful Visualization in Enterprise Analytics

TL;DR

This paper introduces a modular multi-agent LLM framework that automates the data-to-dashboard process, enhancing insight generation and visualization in enterprise analytics without relying on fixed ontologies or templates.

Contribution

It presents a novel, flexible pipeline of LLM agents for automated data analysis and visualization, improving upon existing chart QA systems with domain-aware reasoning.

Findings

Improved insightfulness and domain relevance over baseline models

Enhanced analytical depth demonstrated across multiple datasets

Framework supports human-in-the-loop validation for business analysts

Abstract

The rapid advancement of LLMs has led to the creation of diverse agentic systems in data analysis, utilizing LLMs' capabilities to improve insight generation and visualization. In this paper, we present an agentic system that automates the data-to-dashboard pipeline through modular LLM agents capable of domain detection, concept extraction, multi-perspective analysis generation, and iterative self-reflection. Unlike existing chart QA systems, our framework simulates the analytical reasoning process of business analysts by retrieving domain-relevant knowledge and adapting to diverse datasets without relying on closed ontologies or question templates. We evaluate our system on three datasets across different domains. Benchmarked against GPT-4o with a single-prompt baseline, our approach shows improved insightfulness, domain relevance, and analytical depth, as measured by tailored evaluation metrics and qualitative human assessment. This work contributes a novel modular pipeline to bridge the path from raw data to visualization, and opens new opportunities for human-in-the-loop validation by domain experts in business analytics. All code can be found here: https://github.com/77luvC/D2D_Data2Dashboard