VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing

• URL: http://arxiv.org/abs/2605.15677v1
• Date: Fri, 15 May 2026 06:59:28 GMT
• Title: VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
• Abstract summary: We present VCG-Bench, a unified benchmark for visual-centrictext ttmxGraph tasks.<n> VCG-Bench comprises: (1) a taxonomized dataset of 1,449 diverse diagrams spanning 6 domains and 15 sub-domains, (2) a paradigm definition that integrates Generation (Vision-to-Code) and Editability (Code-to-Code), and (3) a Tailored Evaluation Protocol employing multi-dimensional metrics such as textttmxGraph Execution Success Rate, Style Consistency Score (SCS), etc.
• Score: 37.60481878724908
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks essential for professional workflows. Existing methods predominantly rely on pixel-based synthesis, which operates in probabilistic pixel spaces and is inherently limited in editability and fidelity. Instead, we propose a new Diagram-as-Code paradigm with symbolic logic that leverages mxGraph Extensible Markup Language (XML) for precise diagram generation and editing. We present VCG-Bench, a unified benchmark for visual-centric \texttt{mxGraph} tasks. VCG-Bench comprises: (1) a taxonomized dataset of 1,449 diverse diagrams spanning 6 domains and 15 sub-domains, (2) a paradigm definition that integrates Generation (Vision-to-Code) and Editability (Code-to-Code), (3) a Tailored Evaluation Protocol employing multi-dimensional metrics such as \texttt{mxGraph} Execution Success Rate, Style Consistency Score (SCS), etc. Experimental results highlight the challenges faced by current State-of-the-Art (SOTA) VLMs in structured fidelity and instruction compliance, reflecting their vision and reasoning capabilities.

Related papers

• OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward [8.227370271724162]
  We introduce a novel visual feedback strategy named Visual Interrogation Verifies All (textscViva)<n>textscViva rewards the visual structure of rendered diagrams through a generative approach.<n>We construct M3$2$Diagram, the first large-scale diagram code generation dataset.
  arXiv  Detail & Related papers  (2026-04-07T07:10:24Z)
• EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution [46.35311453619801]
  EvoDiagram is an agentic framework that generates object-level editable diagrams via an intermediate canvas schema.<n>EvoDiagram employs a coordinated multi-agent system to decouple semantic intent from rendering logic.<n>We further release CanvasBench, a benchmark consisting of both data and metrics for canvas-based diagramming.
  arXiv  Detail & Related papers  (2026-02-20T11:11:02Z)
• See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models [34.29171455515379]
  We propose a unified framework that enhances both scalability and modality coordination in graph understanding.<n>For scalability, GraphVista organizes graph information hierarchically into a lightweight GraphRAG base.<n>For modality coordination, GraphVista introduces a planning agent that routes tasks to the most suitable modality.
  arXiv  Detail & Related papers  (2025-10-19T09:20:44Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation [55.01077993490845]
  Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling.<n>We introduce FOCUS, a unified LVLM that integrates segmentation-aware perception and controllable object-centric generation within an end-to-end framework.
  arXiv  Detail & Related papers  (2025-06-20T07:46:40Z)
• Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation [4.246322465055928]
  We propose Draw with Thought (DwT), a training-free framework that guides MLLMs to reconstruct diagrams into editable mxGraph XML code.<n>DwT enables interpretable and controllable outputs without model fine-tuning.<n>We release Plot2XML, a benchmark of 247 real-world scientific diagrams with gold-standard XML annotations.
  arXiv  Detail & Related papers  (2025-04-13T08:22:09Z)
• LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models [87.68057302738457]
  Text-Attributed Graphs (TAGs) are ubiquitous in real-world scenarios.<n>Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, existing approaches suffer from decoupled architectures.<n>We propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning.
  arXiv  Detail & Related papers  (2025-03-05T09:45:22Z)
• HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing [54.970275599061594]
  We design an adaptive evaluation framework, called Hierarchical and Multi-Grained Inconsistency Evaluation (HMGIE)<n>HMGIE can provide multi-grained evaluations covering both accuracy and completeness for various image-caption pairs.<n>To verify the efficacy and flexibility of the proposed framework, we construct MVTID, an image-caption dataset with diverse types and granularities of inconsistencies.
  arXiv  Detail & Related papers  (2024-12-07T15:47:49Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.