nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow
This work addresses the challenge of automating data visualization for users dealing with large-scale, heterogeneous data, representing an incremental advancement in NL2Vis by improving performance on complex queries.
The paper tackles the problem of converting natural language descriptions into visualizations from tabular data, especially for complex queries across multiple tables, by proposing nvAgent, a collaborative agent workflow that achieves a 7.88% improvement in single-table and 9.23% in multi-table scenarios over state-of-the-art baselines.
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.