# VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems

arXiv: https://arxiv.org/abs/2509.11942 · HTML: https://mlsanity.com/paper/2509.11942/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 14 of 14)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Do Users Write More Insecure Code with AI Assistants?](https://mlsanity.com/paper/2211.03622/) (2022)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing](https://mlsanity.com/paper/2411.11916/) (2024)
- [Using AI Assistants in Software Development: A Qualitative Study on Security Practices and Concerns](https://mlsanity.com/paper/2405.06371/) (2024)
- [DocAgent: A Multi-Agent System for Automated Code Documentation Generation](https://mlsanity.com/paper/2504.08725/) (2025)
- [From Today's Code to Tomorrow's Symphony: The AI Transformation of Developer's Routine by 2030](https://mlsanity.com/paper/2405.12731/) (2024)
- [Sketches and Diagrams in Practice](https://mlsanity.com/paper/1706.09172/) (2017)
- [An Exploratory Study of ML Sketches and Visual Code Assistants](https://mlsanity.com/paper/2412.13386/) (2024)
- [Linking Sketches and Diagrams to Source Code Artifacts](https://mlsanity.com/paper/1706.09700/) (2017)
- [Round-Trip Sketches: Supporting the Lifecycle of Software Development Sketches from Analog to Digital and Back](https://mlsanity.com/paper/1708.01787/) (2017)
- [Charting a Path to Efficient Onboarding: The Role of Software Visualization](https://mlsanity.com/paper/2401.09605/) (2024)

## Built on by (most cited first, 1 of 1)

- [DocAtlas: Long-Document Understanding as Mutable-State Interaction](https://mlsanity.com/paper/2608.07527/) (2026)

## Abstract (arXiv)

Visual documentation is an effective tool for reducing the cognitive barrier developers face when understanding unfamiliar code, enabling more intuitive comprehension. Compared to textual documentation, it provides a higher-level understanding of the system structure and data flow. Developers usually prefer visual representations over lengthy textual descriptions for large software systems. Visual documentation is both difficult to produce and challenging to evaluate. Manually creating it is time-consuming, and currently, no existing approach can automatically generate high-level visual documentation directly from code. Its evaluation is often subjective, making it difficult to standardize and automate. To address these challenges, this paper presents the first exploration of using agentic LLM systems to automatically generate visual documentation. We introduce VisDocSketcher, the first agent-based approach that combines static analysis with LLM agents to identify key elements in the code and produce corresponding visual representations. We propose a novel evaluation framework, AutoSketchEval, for assessing the quality of generated visual documentation using code-level metrics. The experimental results show that our approach can valid visual documentation for 74.4% of the samples. It shows an improvement of 26.7-39.8% over a simple template-based baseline. Our evaluation framework can reliably distinguish high-quality (code-aligned) visual documentation from low-quality (non-aligned) ones, achieving an AUC exceeding 0.87. Our work lays the foundation for future research on automated visual documentation by introducing practical tools that not only generate valid visual representations but also reliably assess their quality.