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

arXiv: https://arxiv.org/abs/2502.05036 · HTML: https://mlsanity.com/paper/2502.05036/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 62 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 24 of 24)

- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries](https://mlsanity.com/paper/2008.10723/) (2020)
- [The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models](https://mlsanity.com/paper/2408.07702/) (2024)
- [MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks](https://mlsanity.com/paper/2304.14979/) (2023)
- [Large Language Model for Table Processing: A Survey](https://mlsanity.com/paper/2402.05121/) (2024)
- [WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs](https://mlsanity.com/paper/2404.06369/) (2024)
- [MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning](https://mlsanity.com/paper/2409.12147/) (2024)
- [Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries](https://mlsanity.com/paper/2312.13671/) (2023)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [Visualization Generation with Large Language Models: An Evaluation](https://mlsanity.com/paper/2401.11255/) (2024)
- [nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task](https://mlsanity.com/paper/2112.12926/) (2021)
- [Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study](https://mlsanity.com/paper/2404.17136/) (2024)
- [FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow System](https://mlsanity.com/paper/1908.00681/) (2019)
- [TQA-Bench: Evaluating LLMs for Multi-Table Question Answering](https://mlsanity.com/paper/2411.19504/) (2024)
- [Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization](https://mlsanity.com/paper/2402.07909/) (2024)
- [RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL](https://mlsanity.com/paper/2407.08273/) (2024)
- [Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization](https://mlsanity.com/paper/2303.08697/) (2023)

## Built on by (most cited first, 23 of 23)

- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [CoDA: Agentic Systems for Collaborative Data Visualization](https://mlsanity.com/paper/2510.03194/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [Self-Organizing Agent Network for LLM-based Workflow Automation](https://mlsanity.com/paper/2508.13732/) (2025)
- [ParaView-MCP: An Autonomous Visualization Agent with Direct Tool Use](https://mlsanity.com/paper/2505.07064/) (2025)
- [SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents](https://mlsanity.com/paper/2603.29139/) (2026)
- [VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation](https://mlsanity.com/paper/2506.13326/) (2025)
- [CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom](https://mlsanity.com/paper/2503.01836/) (2025)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?](https://mlsanity.com/paper/2508.03644/) (2025)
- [InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents](https://mlsanity.com/paper/2511.22884/) (2025)
- [MultiVis-Agent: A Multi-Agent Framework with Logic Rules for Reliable and Comprehensive Cross-Modal Data Visualization](https://mlsanity.com/paper/2601.18320/) (2026)
- [MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data](https://mlsanity.com/paper/2512.13297/) (2025)
- [Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions](https://mlsanity.com/paper/2504.16358/) (2025)
- [NL2Dashboard: A Lightweight and Controllable Framework for Generating Dashboards with LLMs](https://mlsanity.com/paper/2601.06126/) (2026)
- [VegaChat: A Robust Framework for LLM-Based Chart Generation and Assessment](https://mlsanity.com/paper/2601.15385/) (2026)
- [DA-Studio: An Agentic System for End-to-End Data Analysis](https://mlsanity.com/paper/2606.31423/) (2026)
- [ALGOGEN: Tool-Generated Verifiable Traces for Reliable Algorithm Visualization](https://mlsanity.com/paper/2605.12159/) (2026)
- [Agentic Authoring of Interactive Multiview Visualizations in Genomics](https://mlsanity.com/paper/2606.00370/) (2026)
- [DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation](https://mlsanity.com/paper/2608.10567/) (2026)
- [VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries](https://mlsanity.com/paper/2609.15182/) (2026)
- [Data Agents: Agentic Data Systems](https://mlsanity.com/paper/2609.24137/) (2026)
- [Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes](https://mlsanity.com/paper/2610.06889/) (2026)

## Abstract (arXiv)

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.