# Can Large Language Models Understand Symbolic Graphics Programs?

arXiv: https://arxiv.org/abs/2408.08313 · HTML: https://mlsanity.com/paper/2408.08313/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 90 of its 122 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 30 of 90)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)

## Built on by (most cited first, 30 of 35)

- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [CAD-Llama: Leveraging Large Language Models for Computer-Aided Design Parametric 3D Model Generation](https://mlsanity.com/paper/2505.04481/) (2025)
- [CAD-Recode: Reverse Engineering CAD Code from Point Clouds](https://mlsanity.com/paper/2412.14042/) (2024)
- [CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers](https://mlsanity.com/paper/2412.13810/) (2024)
- [BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing](https://mlsanity.com/paper/2504.01786/) (2025)
- [InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing](https://mlsanity.com/paper/2603.09877/) (2026)
- [ChatGarment: Garment Estimation, Generation and Editing via Large Language Models](https://mlsanity.com/paper/2412.17811/) (2024)
- [MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh](https://mlsanity.com/paper/2508.01242/) (2025)
- [How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations](https://mlsanity.com/paper/2510.22780/) (2025)
- [Large Language Models for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2505.08137/) (2025)
- [SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation](https://mlsanity.com/paper/2506.03139/) (2025)
- [Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?](https://mlsanity.com/paper/2504.00509/) (2025)
- [InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models](https://mlsanity.com/paper/2510.11341/) (2025)
- [GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs](https://mlsanity.com/paper/2505.17653/) (2025)
- [Generating Symbolic World Models via Test-time Scaling of Large Language Models](https://mlsanity.com/paper/2502.04728/) (2025)
- [JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence](https://mlsanity.com/paper/2510.23538/) (2025)
- [Symbolic Graphics Programming with Large Language Models](https://mlsanity.com/paper/2509.05208/) (2025)
- [Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding](https://mlsanity.com/paper/2603.18472/) (2026)
- [EvoCAD: Evolutionary CAD Code Generation with Vision Language Models](https://mlsanity.com/paper/2510.11631/) (2025)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art](https://mlsanity.com/paper/2410.01733/) (2024)
- [PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation](https://mlsanity.com/paper/2607.01883/) (2026)
- [Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review](https://mlsanity.com/paper/2503.04983/) (2025)
- [BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning](https://mlsanity.com/paper/2602.22284/) (2026)
- [CodePercept: Code-Grounded Visual STEM Perception for MLLMs](https://mlsanity.com/paper/2603.10757/) (2026)
- [UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD](https://mlsanity.com/paper/2606.05058/) (2026)
- [Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure](https://mlsanity.com/paper/2512.14336/) (2025)
- [mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval](https://mlsanity.com/paper/2604.17054/) (2026)
- [PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning](https://mlsanity.com/paper/2605.19382/) (2026)
- [DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing](https://mlsanity.com/paper/2607.02290/) (2026)

## Abstract (arXiv)

Against the backdrop of enthusiasm for large language models (LLMs), there is a growing need to scientifically assess their capabilities and shortcomings. This is nontrivial in part because it is difficult to find tasks which the models have not encountered during training. Utilizing symbolic graphics programs, we propose a domain well-suited to test multiple spatial-semantic reasoning skills of LLMs. Popular in computer graphics, these programs procedurally generate visual data. While LLMs exhibit impressive skills in general program synthesis and analysis, symbolic graphics programs offer a new layer of evaluation: they allow us to test an LLM's ability to answer semantic questions about the images or 3D geometries without a vision encoder. To semantically understand the symbolic programs, LLMs would need to possess the ability to "imagine" and reason how the corresponding graphics content would look with only the symbolic description of the local curvatures and strokes. We use this task to evaluate LLMs by creating a large benchmark for the semantic visual understanding of symbolic graphics programs, built procedurally with minimal human effort. Particular emphasis is placed on transformations of images that leave the image level semantics invariant while introducing significant changes to the underlying program. We evaluate commercial and open-source LLMs on our benchmark to assess their ability to reason about visual output of programs, finding that LLMs considered stronger at reasoning generally perform better. Lastly, we introduce a novel method to improve this ability -- Symbolic Instruction Tuning (SIT), in which the LLM is finetuned with pre-collected instruction data on symbolic graphics programs. Interestingly, we find that SIT not only improves LLM's understanding on symbolic programs, but it also improves general reasoning ability on various other benchmarks.