nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow

TL;DR

nvAgent is a collaborative multi-agent system that converts natural language descriptions into data visualizations, effectively handling complex queries across multiple tables and outperforming existing methods.

Contribution

The paper introduces nvAgent, a novel multi-agent framework that enhances NL2Vis by improving reasoning and visualization generation from complex, multi-table data sources.

Findings

Achieves 7.88% improvement on single-table visualization tasks

Achieves 9.23% improvement on multi-table visualization tasks

Maintains nearly 20% performance margin over previous models

Abstract

Natural Language to Visualization (NL2Vis) seeks to convert natural-language descriptions into visual representations of given tables, empowering users to derive insights from large-scale data. Recent advancements in Large Language Models (LLMs) show promise in automating code generation to transform tabular data into accessible visualizations. However, they often struggle with complex queries that require reasoning across multiple tables. To address this limitation, we propose a collaborative agent workflow, termed nvAgent, for NL2Vis. Specifically, nvAgent comprises three agents: a processor agent for database processing and context filtering, a composer agent for planning visualization generation, and a validator agent for code translation and output verification. Comprehensive evaluations on the new VisEval benchmark demonstrate that nvAgent consistently surpasses state-of-the-art baselines, achieving a 7.88% improvement in single-table and a 9.23% improvement in multi-table scenarios. Qualitative analyses further highlight that nvAgent maintains nearly a 20% performance margin over previous models, underscoring its capacity to produce high-quality visual representations from complex, heterogeneous data sources.