# SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection

arXiv: https://arxiv.org/abs/2509.07473 · HTML: https://mlsanity.com/paper/2509.07473/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs](https://mlsanity.com/paper/2502.17422/) (2025)
- [Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning](https://mlsanity.com/paper/2401.06805/) (2024)
- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://mlsanity.com/paper/2006.14615/) (2020)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [Neural Design Network: Graphic Layout Generation with Constraints](https://mlsanity.com/paper/1912.09421/) (2019)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [Attribute-conditioned Layout GAN for Automatic Graphic Design](https://mlsanity.com/paper/2009.05284/) (2020)
- [PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout](https://mlsanity.com/paper/2303.15937/) (2023)
- [LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction](https://mlsanity.com/paper/2208.08037/) (2022)
- [PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM](https://mlsanity.com/paper/2406.02884/) (2024)
- [Graphic Design with Large Multimodal Model](https://mlsanity.com/paper/2404.14368/) (2024)
- [PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation](https://mlsanity.com/paper/2505.07843/) (2025)
- [VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction](https://mlsanity.com/paper/2412.04237/) (2024)
- [DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach](https://mlsanity.com/paper/2501.15142/) (2025)
- [Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Models](https://mlsanity.com/paper/2110.07775/) (2021)
- [Fast-Slow-Thinking: Complex Task Solving with Large Language Models](https://mlsanity.com/paper/2504.08690/) (2025)
- [LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation](https://mlsanity.com/paper/2504.10829/) (2025)
- [Revision Matters: Generative Design Guided by Revision Edits](https://mlsanity.com/paper/2406.18559/) (2024)
- [CoLay: Controllable Layout Generation through Multi-conditional Latent Diffusion](https://mlsanity.com/paper/2405.13045/) (2024)
- [Large Language Models for Predictive Analysis: How Far Are They?](https://mlsanity.com/paper/2505.17149/) (2025)
- [Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity](https://mlsanity.com/paper/2508.06034/) (2025)

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

- [Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs](https://mlsanity.com/paper/2511.20892/) (2025)

## Abstract (arXiv)

Spreadsheets are critical to data-centric tasks, with rich, structured layouts that enable efficient information transmission. Given the time and expertise required for manual spreadsheet layout design, there is an urgent need for automated solutions. However, existing automated layout models are ill-suited to spreadsheets, as they often (1) treat components as axis-aligned rectangles with continuous coordinates, overlooking the inherently discrete, grid-based structure of spreadsheets; and (2) neglect interrelated semantics, such as data dependencies and contextual links, unique to spreadsheets. In this paper, we first formalize the spreadsheet layout generation task, supported by a seven-criterion evaluation protocol and a dataset of 3,326 spreadsheets. We then introduce SheetDesigner, a zero-shot and training-free framework using Multimodal Large Language Models (MLLMs) that combines rule and vision reflection for component placement and content population. SheetDesigner outperforms five baselines by at least 22.6%. We further find that through vision modality, MLLMs handle overlap and balance well but struggle with alignment, necessitates hybrid rule and visual reflection strategies. Our codes and data is available at Github.