Agentic Pipeline 实现流程图多比例自适应重排，Content Fidelity 达 68.6%
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline
写论文的都懂流程图换个画布比例多痛苦，这篇把它做成智能体流水线，输出还是 draw.io 能直接编辑的，比图生图和文生图靠谱多了。
论文将流程图按目标宽高比重排定义为一个独立任务，输入栅格流程图，输出结构忠实、无幻觉且可编辑的版式。该方法拆分为 Parse、Style、Layout 三个阶段的智能体流水线，每个阶段由主智能体搭配一个 Critic，用确定性约束检查加 VLM 视觉反馈来显式校验连线连通性，输出为 draw.io 可编辑的 mxGraph XML。在包含 100 张流程图、五种宽高比的基准上，由 Gemini 3.1 Pro 评分并与人类判断对照验证，方法取得 68.6% 的 Content Fidelity，而此前方法仅为 11.2% 到 41.4%。
One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline
Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 phone previews. Each format imposes a different aspect ratio on the same computational graph, where any silently broken connection misrepresents the method. We formulate aspect-ratio-adaptive flowchart relayout as a distinct task: given a raster flowchart and a target ratio, produce a structurally faithful, hallucination-free, editable layout. Existing methods fail characteristically: image-to-image models stretch blocks and reject extreme ratios, text-to-image agentic systems hallucinate content, and parse-then-render systems mis-route edges. We propose an agentic pipeline factored into Parse, Style, and Layout stages, each pairing a main agent with a critic that combines deterministic constraint checks with VLM visual feedback so connectivity is explicitly checked and prevented from being silently broken. Outputs are draw.io-editable mxGraph XML. On a curated benchmark of 100 flowcharts at five aspect ratios, evaluated by Gemini 3.1 Pro and validated against human judgments, our method reaches 68.6% Content Fidelity versus 11.2-41.4% for prior work. Project page: https://onefigureeverycanvas.vercel.app/
