# Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis

arXiv: https://arxiv.org/abs/2603.07936 · HTML: https://mlsanity.com/paper/2603.07936/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 13 of 13)

- [ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation](https://mlsanity.com/paper/2501.06598/) (2025)
- [SciCap: Generating Captions for Scientific Figures](https://mlsanity.com/paper/2110.11624/) (2021)
- [SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning](https://mlsanity.com/paper/2306.03491/) (2023)
- [TikZero: Zero-Shot Text-Guided Graphics Program Synthesis](https://mlsanity.com/paper/2503.11509/) (2025)
- [ScImage: How Good Are Multimodal Large Language Models at Scientific Text-to-Image Generation?](https://mlsanity.com/paper/2412.02368/) (2024)
- [Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization](https://mlsanity.com/paper/2509.09307/) (2025)
- [A Review on Generative AI For Text-To-Image and Image-To-Image Generation and Implications To Scientific Images](https://mlsanity.com/paper/2502.21151/) (2025)
- [DiagramEval: Evaluating LLM-Generated Diagrams via Graphs](https://mlsanity.com/paper/2510.25761/) (2025)
- [PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures](https://mlsanity.com/paper/2501.15074/) (2025)
- [ChartCap: Mitigating Hallucination of Dense Chart Captioning](https://mlsanity.com/paper/2508.03164/) (2025)
- [Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts](https://mlsanity.com/paper/2503.04095/) (2025)
- [A Comparative Analysis of Text-to-Image Generative AI Models in Scientific Contexts: A Case Study on Nuclear Power](https://mlsanity.com/paper/2312.01180/) (2023)
- [Pluto: Authoring Semantically Aligned Text and Charts for Data-Driven Communication](https://mlsanity.com/paper/2502.07725/) (2025)

## Abstract (arXiv)

Diagrams are widely used in teaching computer science courses. They are useful in subjects such as automata and formal languages, data structures, etc. These diagrams, often drawn by students during exams or assignments, vary in structure, layout, and correctness. This study examines whether current vision-language and large language models can process such diagrams and produce accurate textual and digital representations. In this study, scanned student-drawn diagrams are used as input. Then, textual descriptions are generated from these images using a vision-language model. The descriptions are checked and revised by human reviewers to make them accurate. Both the generated and the revised descriptions are then fed to a large language model to generate TikZ code. The resulting diagrams are compiled and then evaluated against the original scanned diagrams. We found descriptions generated directly from images using vision-language models are often incorrect and human correction can substantially improve the quality of vision language model generated descriptions. This research can help computer science education by paving the way for automated grading and feedback and creating more accessible instructional materials.