# ChatVis: Large Language Model Agent for Generating Scientific Visualizations

arXiv: https://arxiv.org/abs/2507.23096 · HTML: https://mlsanity.com/paper/2507.23096/

## Key facts

- Cited by 7 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 32 of its 47 references that are in the map.
- First posted on arXiv 30 Jul 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, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [SciCode: A Research Coding Benchmark Curated by Scientists](https://mlsanity.com/paper/2407.13168/) (2024)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [ReACC: A Retrieval-Augmented Code Completion Framework](https://mlsanity.com/paper/2203.07722/) (2022)
- [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://mlsanity.com/paper/2006.05405/) (2020)
- [Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model](https://mlsanity.com/paper/2010.09142/) (2020)
- [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023)
- [VisEval: A Benchmark for Data Visualization in the Era of Large Language Models](https://mlsanity.com/paper/2407.00981/) (2024)
- [An Unsupervised Information-Theoretic Perceptual Quality Metric](https://mlsanity.com/paper/2006.06752/) (2020)
- [DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts](https://mlsanity.com/paper/2408.05346/) (2024)
- [HPC-GPT: Integrating Large Language Model for High-Performance Computing](https://mlsanity.com/paper/2311.12833/) (2023)
- [AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging](https://mlsanity.com/paper/2109.14053/) (2021)
- [LM4HPC: Towards Effective Language Model Application in High-Performance Computing](https://mlsanity.com/paper/2306.14979/) (2023)
- [ChatVis: Automating Scientific Visualization with a Large Language Model](https://mlsanity.com/paper/2410.11863/) (2024)
- [Text-based Transfer Function Design for Semantic Volume Rendering](https://mlsanity.com/paper/2406.15634/) (2024)

## Built on by (most cited first, 7 of 7)

- [SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents](https://mlsanity.com/paper/2603.29139/) (2026)
- [TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization](https://mlsanity.com/paper/2603.25063/) (2026)
- [Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks](https://mlsanity.com/paper/2605.21825/) (2026)
- [Exploring LLM Agent Designs and Interaction Modalities for Scientific Visualization](https://mlsanity.com/paper/2604.27996/) (2026)
- [HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization](https://mlsanity.com/paper/2606.26614/) (2026)
- [The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality](https://mlsanity.com/paper/2603.16873/) (2026)
- [SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization](https://mlsanity.com/paper/2606.05525/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are rapidly increasing in capability, but they still struggle with highly specialized programming tasks such as scientific visualization. We present an LLM assistant, ChatVis, that aids the LLM to generate Python code for ParaView scientific visualization tasks, without the need for retraining or fine-tuning the LLM. ChatVis employs chain-of-thought prompt simplification, retrieval-augmented prompt generation using a vector database of documentation and code examples, and error checking with iterative prompt feedback to correct errors until a visualization is produced. An integral part of our approach is a benchmark suite of canonical visualization tasks, ParaView regression tests, and scientific use cases that includes comprehensive evaluation metrics. We evaluate our visualization assistant by comparing results with a variety of top-performing unassisted LLMs. We find that all the metrics are significantly improved with ChatVis.