SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.05036 · ACL · 2025

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

Dongping Chen, Yao Wan, Yi Gui, Hongyu Zhang, Geliang Ouyang, Jingyao Chen, Zhihe Nie

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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: processor for database processing and context filtering, composer for planning visualization generation, and validator for code translation and output verification. Comprehensive evaluations on the VisEval benchmark demonstrate that NVAGENT consistently surpasses state-ofthe-art baselines, achieving 7.88% and 9.23% improvements in single-and multi-table scenarios. Qualitative analyses further highlight that NVAGENT maintains nearly a 20% performance margin over previous methods, underscoring its capacity to produce high-quality visual representations from complex, heterogeneous data sources. All datasets and source code are available at: https://github.com/ geliang0114/nvAgent. *

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.05036")
get_code_for_paper("2502.05036")
have("2502.05036")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2502.05036.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2502.05036.svg)](https://syntology.ai/paper/2502.05036)

Connect an agent — have() is free.