English

OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward

Artificial Intelligence 2026-04-08 v1

Abstract

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 (\textsc{Viva}). Unlike brittle syntax-based rules or pixel-level matching, \textsc{Viva} rewards the visual structure of rendered diagrams through a generative approach. Specifically, \textsc{Viva} 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 M32^2Diagram, the first large-scale diagram code generation dataset, containing over 196k high-quality instances. Experimental results confirm that the combination of SFT and our \textsc{Viva}-based RL allows OmniDiagram to establish a new state-of-the-art (SOTA) across diagram code generation benchmarks.

Keywords

Cite

@article{arxiv.2604.05514,
  title  = {OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward},
  author = {Haoyue Yang and Xuanle Zhao and Xuexin Liu and Feibang Jiang and Yao Zhu},
  journal= {arXiv preprint arXiv:2604.05514},
  year   = {2026}
}

Comments

Accepted to ACL 2026 Findings

R2 v1 2026-07-01T11:56:49.103Z