# OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward

arXiv: https://arxiv.org/abs/2604.05514 · HTML: https://mlsanity.com/paper/2604.05514/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs](https://mlsanity.com/paper/2406.18629/) (2024)
- [ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation](https://mlsanity.com/paper/2501.06598/) (2025)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation](https://mlsanity.com/paper/2502.14846/) (2025)
- [Rendering-Aware Reinforcement Learning for Vector Graphics Generation](https://mlsanity.com/paper/2505.20793/) (2025)
- [ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing](https://mlsanity.com/paper/2505.11935/) (2025)
- [FlowVQA: Mapping Multimodal Logic in Visual Question Answering with Flowcharts](https://mlsanity.com/paper/2406.19237/) (2024)
- [VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning](https://mlsanity.com/paper/2511.00391/) (2025)
- [nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning](https://mlsanity.com/paper/2503.12880/) (2025)
- [Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation](https://mlsanity.com/paper/2508.13587/) (2025)
- [ChartMaster: Advancing Chart-to-Code Generation with Real-World Charts and Chart Similarity Reinforcement Learning](https://mlsanity.com/paper/2508.17608/) (2025)
- [Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text](https://mlsanity.com/paper/2507.19969/) (2025)
- [ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing](https://mlsanity.com/paper/2511.15266/) (2025)
- [JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence](https://mlsanity.com/paper/2510.23538/) (2025)
- [Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability](https://mlsanity.com/paper/2506.02073/) (2025)
- [StarFlow: Generating Structured Workflow Outputs From Sketch Images](https://mlsanity.com/paper/2503.21889/) (2025)
- [Multilingual Multimodal Software Developer for Code Generation](https://mlsanity.com/paper/2507.08719/) (2025)
- [Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents](https://mlsanity.com/paper/2507.14819/) (2025)

## Built on by (most cited first, 4 of 4)

- [Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs](https://mlsanity.com/paper/2605.30611/) (2026)
- [Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence](https://mlsanity.com/paper/2606.15932/) (2026)
- [EdiTikZ: Scientific Figure Editing from Revision Trajectories](https://mlsanity.com/paper/2609.01409/) (2026)
- [FigAct: Turning Scientific Figures into Active Canvases for Explanation](https://mlsanity.com/paper/2609.36190/) (2026)

## Abstract (arXiv)

The paradigm of programmable diagram generation is evolving rapidly, playing a crucial role in structured visualization. However, most existing studies are confined to a narrow range of task formulations and language support, constraining their applicability to diverse diagram types. In this work, we propose OmniDiagram, a unified framework that incorporates diverse diagram code languages and task definitions. To address the challenge of aligning code logic with visual fidelity in Reinforcement Learning (RL), we introduce a novel visual feedback strategy named Visual Interrogation Verifies All (textscViva). Unlike brittle syntax-based rules or pixel-level matching, textscViva rewards the visual structure of rendered diagrams through a generative approach. Specifically, textscViva actively generates targeted visual inquiries to scrutinize diagram visual fidelity and provides fine-grained feedback for optimization. This mechanism facilitates a self-evolving training process, effectively obviating the need for manually annotated ground truth code. Furthermore, we construct M32Diagram, the first large-scale diagram code generation dataset, containing over 196k high-quality instances. Experimental results confirm that the combination of SFT and our textscViva-based RL allows OmniDiagram to establish a new state-of-the-art (SOTA) across diagram code generation benchmarks.