One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline

Shih-Chen Tseng; Chih-Hsuan Chen; Ryan Yang; Hsi-An Chen; Chun-Wei Tuan Mu; Yu-Lun Liu

cs.CVOct 5, 2026

One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipeline

Authors: Shih-Chen Tseng, Chih-Hsuan Chen, Ryan Yang, Hsi-An Chen, Chun-Wei Tuan Mu, Yu-Lun Liu

Organizations: Department of Computer Science, National Yang Ming Chiao Tung University · Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign

Abstract

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/

Figures & tables

Figure 1: Aspect-ratio-adaptive flowchart relayout. Given a single flowchart at one fixed ratio (left) , our method produces structure-preserving relayouts at arbitrary aspect ratios (right) : phone, tablet, social, slide, and banner. Three different source figures (top to bottom) demonstrate generality across architecture diagrams, experimental pipelines, and process flows. Outputs are not re-rendered images but draw.io-editable XML, ready for further manual refinement.

Figure 2: Three categorical failure modes on flowchart relayout. Given input (a) at 1:1 and a request for 3:2, we examine three families. (b) Image-to-image models (e.g., Nano Banana Pro) resize in pixel space, stretching embedded frames and blocks, and they also reject aspect ratios outside 3:1–1:3. (c) Text-to-image agentic systems (e.g., PaperBanana) re-synthesize from a prompt, dropping blocks present in (a) and adding labels that were not. (d) Parse-then-render systems (e.g., AutoFigure-Edit, SciFig) recover components but mis-route edges, breaking the computational graph. Red annotations mark each failure. None achieves structural fidelity, hallucination-freedom, and arbitrary resizing simultaneously. These are the three properties our task requires.

Method	Style Control	Canvas Resizing	Editable Format
Image-to-image models
Nano Banana Pro	Image reference	$\triangle$ (~3:1 to 1:3)	×
GPT Image 2.0	Image reference	$\triangle$ (3:1 to 1:3)	×
Text-to-image / agentic systems
SciFig ( Huang et al., 2026b )	Prompt (Hard)	×	×
PaperBanana ( Zhu et al., 2026a )	Prompt (Hard)	$\triangle$ (~3:1 to 1:3)	×

Table 1: Capability comparison with prior work. We compare against three families of figure-generation approaches along three axes for paper-figure relayout: how style is specified, what canvas ratios are supported, and whether outputs are editable in a standard tool. Only ours achieves all three: image-reference style control, arbitrary aspect ratios, and draw.io compatibility.

\checkmark

= full support,

\triangle

= partial support, ×= none.

Figure 3: Overview of our agentic relayout pipeline. Given input flowchart $F_{0}$ (raster, here 4:3) and target aspect ratio $r$ (here 16:9), our method produces draw.io-editable XML $X^{*}$ in three stages, each pairing a main agent with a critic that iterates until convergence. (a) Parse converts $F_{0}$ into structured XML $X$ by combining SAM 3 instance segmentation (bounding boxes for every component) with a VLM-based parse agent. (b) Style produces styled XML $\hat{X}$ from $X$ and $F_{0}$ ; we extract dominant colors directly from $F_{0}$ ’s pixels with PIL, since VLM color perception is unreliable. (c) Layout extracts inter-block relationships from $\hat{X}$ and rearranges components into canvas $r$ via DAG-based hierarchical layering; the critic verifies no relationship is broken and no same-level components newly overlap. Output $X^{*}$ preserves the structure, style, and content of $F_{0}$ while fitting the new aspect ratio.

Figure 4: Iterative critic refinement across pipeline stages. (a) The Parse Stage combines deterministic checks and VLM feedback to progressively correct out-of-bound components and edge errors, yielding the parsed XML $X$ . (b) The Style Stage transfers colors, typography, and corner radius, while critic feedback corrects residual font and shape mismatches. (c) The Layout Stage applies DAG-based hierarchical relayout and iteratively resolves boundary, overlap, and routing issues, producing the final layout $X^{*}$ .

Figure 5: Editable XML output in draw.io. (a) The generated $X^{*}$ can be opened directly in draw.io, where each block, label, connector, and style attribute remains editable. (b) Users can modify fonts, borders, colors, and component positions independently, while explicit source/target references preserve connector relationships after editing.

Image-to-image
	Correctness (%) $\uparrow$			Visual Quality $\downarrow$
Method	Relationship	Hallu.-free	Content	Layout	Style	Overall $\uparrow$
Nano Banana Pro	49.8	69.4	41.4	2.85	1.35	71.10
GPT Image 2.0	50.2	75.4	40.2	3.17	2.08	71.10
T2I / agentic
PaperBanana ( Zhu et al., 2026a )	38.4	18.6	11.2	2.14	4.34	39.05

Table 2: Quantitative comparison on FlowchartRelayoutBench . Five methods across three families are evaluated under Correctness, Visual Quality, and Overall, a hierarchical score prioritizing Content Fidelity over Visual Quality. Our method achieves the best Correctness metrics and Overall score (81.85, 1.15

\times

the next-best). PaperBanana ranks best on Layout despite weak correctness, while Nano Banana Pro and GPT Image 2.0 rank well on Style by largely preserving the original appearance. Bold = best, underline = second-best, italic = third-best.

Panel of Figure 6 — Figure 6: Qualitative comparison under different target aspect ratios. We compare our method with four baselines at three target ratios: 1:1, 2:3, and 3:2. GPT Image 2.0 typically compresses or crops the original; Nano Banana Pro attempts relayout more often but tends to break relationships. PaperBanana rotates horizontal layouts to fit portrait canvases, and AutoFigure-Edit may introduce hallucinated elements or inconsistent relationships. Ours preserves relationships, avoids hallucinations, uses the canvas effectively, and produces editable XML. Please zoom in for details.

Panel of Figure 7 — Figure 7: User study results. We report human evaluation results for content-related metrics and visual-quality metrics. Our method achieves the best performance on Relationship Preservation and Hallucination-free Rate, and shows strong pairwise win rates in Layout Quality and Style Similarity.

Metric	Statistic	Corr.	Agreement	95% CI
Relationship	$\phi$	0.671	83.2%	[0.560, 0.753]
Hallucination	$\phi$	0.593	82.0%	[0.486, 0.693]
Layout	$\rho$	0.620	–	[0.513, 0.714]
Style	$\rho$	0.757	–	[0.704, 0.807]

Table 3: Agreement between VLM-as-a-Judge and human evaluation. We report Phi coefficient (

\phi

) and classification agreement for binary Relationship Preservation and Hallucination-free judgments, and Spearman’s rank correlation (

\rho

) for Layout Quality and Style Similarity. All correlations are significant at

p<0.001

Direct prompting / decomposition
Method	Rel. $\uparrow$	Hallu.-free $\uparrow$	Content $\uparrow$	Layout $\downarrow$	Style $\downarrow$	Overall $\uparrow$
Direct Prompt Parse Stage	53.3	60.0	33.3	5.00	7.67	50.74
Direct Prompt Layout Stage	70.0	93.3	66.7	4.07	5.03	69.26
Direct Prompt VLM-to-XML (Gemini 3.1 Pro)	43.3	50.0	33.3	5.23	6.87	41.11
Direct Prompt VLM-to-XML (GPT-5.5)	33.3	80.0	30.0	4.97	7.77	49.63
Stage / Critic removal

Table 4: Quantitative ablation study on 30 flowcharts. We compare direct prompting, Stage/Critic removal, and Graphviz DOT replacement. Layout, Style, and Overall are computed jointly within the ablation and are therefore not directly comparable with Table 2 . Bold = best, underline = second-best, italic = third-best.

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Complexity	Method	Relationship	Hallu.-free	Content	Layout	Style	Overall $\uparrow$
		Correctness (%) $\uparrow$			Visual Quality $\downarrow$
Easy [2pt]Nodes: 10.1 $\pm$ 3.4 Edges: 9.4 $\pm$ 3.3	Nano Banana Pro	62.4	77.6	56.0	2.78	1.54	69.40
	GPT Image 2.0	66.4	83.2	56.8	3.01	2.09	70.00
	PaperBanana	52.0	25.6	18.4	2.36	4.50	33.20
	AutoFigure-Edit	61.6	48.8	39.2	3.62	3.88	45.00
	Ours	93.6	98.4	92.8	2.46	2.86	80.60

Appendix

Table 5: Performance across source-diagram structural complexity. Results are reported on the easy, medium, and hard subsets of FlowchartRelayoutBench . Overall follows the hierarchical scoring in Table 2 . Our method achieves the highest Content Fidelity and Overall score at all three complexity levels. Bold = best, underline = second-best, and italic = third-best within each level.

Complexity	Parse	Style	Layout	Total
Easy	$2.33\pm 0.80$	$1.63\pm 0.48$	$4.42\pm 1.088$	$8.38\pm 1.68$
Medium	$2.56\pm 0.59$	$1.82\pm 0.38$	$4.74\pm 0.78$	$9.13\pm 1.04$
Hard	$2.65\pm 0.67$	$1.81\pm 0.39$	$4.89\pm 0.45$	$9.35\pm 0.96$

Appendix

Table 6: Refinement Iterations by Structural Complexity. Average refinement iterations (mean

\pm

std.) for the Parse, Style, and Layout stages and the full pipeline. The maximum iteration budgets are 3, 2, and 5, respectively.

Figure 8: Direct Prompt Layout Stage. Direct prompting leaves substantial unused space and adapts to the target canvas by excessively shrinking components. Our method makes more effective use of the available canvas while largely preserving component sizes and maintaining clear connector flow.

Figure 9: Without Parse Critic. Structural errors from the initial parse remain uncorrected, including incorrect shape types and mismatched connector attachment points. Iterative Critic feedback improves both component geometry and edge anchoring.

Figure 10: Without Style Stage. The reconstructed diagram exhibits mismatched block colors, missing or simplified containers, inconsistent connector styles, and typography differences. The Style Stage substantially improves visual correspondence while preserving the recovered structure.

Figure 11: Without Layout Critic. The single-pass result exhibits weaker space utilization, less natural arrow routing, and poorer visual balance. Iterative deterministic and visual feedback improves placement, compactness, and readability while preserving connectivity.

Figure 12: Replacing Layout Stage with Graphviz DOT. The topology-driven layout often leaves substantial unused space and may fail to preserve relationships involving container structures. Our Layout Stage better utilizes the target canvas while maintaining these structural relationships.

Method	XML Fail. $\downarrow$	Rel. $\uparrow$	Hallu.-free $\uparrow$	Content $\uparrow$	Layout $\downarrow$	Style $\downarrow$	Overall $\uparrow$
Direct VLM-to-XML (Qwen3.6-27B)	16.0	8.0	12.0	0.0	2.36	2.28	38.0
Direct I2I (Qwen-Image-Edit-2511)	0.0	24.0	8.0	8.0	2.16	2.20	40.0
Ours (Qwen3.6-27B)	0.0	20.0	52.0	20.0	1.40	1.44	90.0

Appendix

Table 7: Transfer to an open-weight VLM. We replace Gemini 3.1 Pro Preview with Qwen3.6-27B while keeping the proposed pipeline unchanged. Although absolute structural fidelity decreases with the open-weight model, our pipeline substantially improves over direct XML generation using the same VLM and eliminates XML-format failures. Overall is computed within this three-method comparison and is not directly comparable with Overall scores in Tables 2 and 4 . Bold = best, underline = second-best, italic = third-best.

Panel of Figure 13 — Figure 13: Qualitative comparison using open-weight Qwen models under the 1:1 target aspect ratio. Direct VLM-to-XML introduces structural and connectivity errors, including overlapping blocks. Direct I2I preserves most visual elements but exhibits missing components, distorted text, and substantial geometric stretching. Our method instead produces a coherent relayout with less distortion while better preserving the original structure and connectivity.

Figure 14: Style transfer results. Given a completed relayout (a) and an unrelated reference $R$ (b), our Style Transfer extension produces $X^{*}_{R}$ (c) that adopts $R$ ’s fill colors, typography, corner style, and connectors while preserving (a)’s block connectivity and semantic content. Colors are transferred via semantic role assignment (background, primary fill, connector) rather than pixel matching, since (a) and $R$ share no spatial correspondence.

Panel of Figure 15 — Figure 15: Additional qualitative comparison under the 1:1 target aspect ratio. In the left example, Nano Banana Pro and GPT Image 2.0 introduce relationship errors when attempting relayout. In the middle and right examples, only our method performs clear relayout, while Nano Banana Pro, GPT Image 2.0, and AutoFigure-Edit mainly rely on stretching, compression, or direct reuse of the original image.

Panel of Figure 16 — Figure 16: Additional qualitative comparison under the 2:3 target aspect ratio. In the left example, Nano Banana Pro and GPT Image 2.0 mostly stretch the original image without meaningful relayout. In the middle example, all baselines introduce relationship errors after relayout. In the right example, GPT Image 2.0 and AutoFigure-Edit leave large unused space, while PaperBanana rotates a horizontal layout to fit the portrait canvas.

Panel of Figure 17 — Figure 17: Additional qualitative comparison under the 3:2 target aspect ratio. In the left example, Nano Banana Pro and PaperBanana introduce many hallucinated elements, while only our method performs clear relayout. In the middle example, Nano Banana Pro and PaperBanana also hallucinate structures, and AutoFigure-Edit and GPT Image 2.0 leave large unused space. In the right example, Nano Banana Pro, GPT Image 2.0, and AutoFigure-Edit mostly stretch the original image without meaningful relayout.

Panel of Figure 18 — Figure 18: Additional qualitative comparison under the 9:16 target aspect ratio. In the left example, all four baselines introduce relationship errors, while our method preserves the correct flow structure. In the middle example, Nano Banana Pro introduces relationship errors after relayout, GPT Image 2.0 mainly stretches the original image, and AutoFigure-Edit leaves large unused space. In the right example, Nano Banana Pro, GPT Image 2.0, and AutoFigure-Edit all produce relationship errors, while PaperBanana rotates a horizontal layout to fit the portrait canvas.

Panel of Figure 19 — Figure 19: Additional qualitative comparison under the 16:9 target aspect ratio. In the left example, Nano Banana Pro and GPT Image 2.0 directly stretch the original image, causing the embedded image blocks to deform, while PaperBanana and AutoFigure-Edit introduce hallucinated elements. In the middle example, Nano Banana Pro, GPT Image 2.0, and AutoFigure-Edit leave large blank regions, while PaperBanana produces many hallucinated structures. In the right example, Nano Banana Pro, GPT Image 2.0, and PaperBanana largely keep the original layout without meaningful relayout, and AutoFigure-Edit leaves large unused space. Only our method performs clear relayout to better adapt the layout to the target canvas.

Explore similar work

Aug 1, 2026cs.CV

DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable

Recent image-generation models and multimodal agents can produce high-quality visuals for increasingly complex visual communication tasks. Yet their raster outputs remain difficult to use directly because meaningful content and relationships are flattened into pixels, preventing users from inspecting, modifying, rearranging, or reusing individual components. We formulate image-to-editable reconstruction, which recovers a structured, directly manipulable artifact from a raster image while preserving its visual and semantic content. The central challenge is to jointly satisfy Fidelity and Editability, which often trade off in practice. To study this task, we introduce DrawAI, comprising an agentic benchmark, DrawAI-Bench, and a reconstruction workflow, DrawAI-Flow. DrawAI-Bench spans scientific figures, presentation slides, posters, and diagrams, combining real and AI-generated images to reflect practical visual-creation scenarios. It evaluates Fidelity and Editability through a hybrid protocol of 39 criteria: deterministic rule-based metrics measure properties with direct correspondences, while asset-specific vision-language rubrics capture semantic and perceptual qualities for which exact matching is misleading. Besides, we propose DrawAI-Flow, a two-stage agentic workflow in which a Parser Agent turns extracted elements evidence into an explicit reconstruction plan, and a Reconstruction Agent realizes the plan as executable graphics code through an iterative code-render-validate-revise loop. On DrawAI-Bench, we systematically evaluate thirteen models across five agent harnesses to study the effects of model capability, harness choice, and workflow design. The results show that reconstruction quality and costs vary substantially across model-harness configurations, while DrawAI-Flow consistently improves editable structure.

Pu Cao, Qingye Kong, Xuedan Yin +5

Beijing University of Posts and Telecommunications · Tsinghua University · Beijing Institute of Technology

Agentic Workflow Design Agentic Benchmarks

Ask PDF

Sep 27, 2026cs.CV

InfoEdit: Probing Global Layout Reasoning in Infographic Editing

Multimodal foundation models edit natural photographs at production quality, yet the same models struggle with structured visual content such as infographics. Unlike photographs, infographics encode information through logical relations; editing one element often requires surrounding elements to be adapted. We refer to this global layout reasoning capability as reflow. Existing image-editing benchmarks neither provide a dedicated setting for structured visual content nor evaluate the reflow capability. We introduce InfoEdit, a novel benchmark of 1,000 infographics across eight logical-relation families, paired with 4,000 editing instructions across four editing tasks, and a reflow-aware evaluation protocol. Across eight frontier editors, only GPT-Image-2 clears 60% average success rate; most models fall below 7%, and no editor exceeds 36% on the Swap-Block task even with perfect target localization. We further show that code-level editing can match the strongest pixel-level editor, revealing complementary strengths across tasks. InfoEdit identifies reflow as a central challenge in structured visual content editing and provides a diagnostic benchmark to facilitate future progress.

Cheng Yang, Chufan Shi, Huijuan Wang +6

University of California San Diego · University of Southern California · University of Illinois Urbana-Champaign +1

Multi-Image Editing Benchmarks Layouts

Ask PDF

May 26, 2026cs.SE

EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering

Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversion of these flowcharts into machine-readable models for RE activities, yet, when directly applied to flowchart conversion, they often fail on topology-critical visual details. To address this, we propose EdgeFlow that augments a VLM's original input with a deterministically extracted Canny edge map-acting as a structural prior-to improve flowchart-to-Mermaid conversion, without requiring annotated training data or domain-specific model fine-tuning. We evaluate EdgeFlow on IndusReqFlow, a dataset sourced from real-world requirements. Compared with off-the-shelf VLMs, EdgeFlow improves node-level F1 by 17.39 percentage points and edge-level F1 by 16.94 percentage points. At the path level, EdgeFlow improves path F1 by 11.06 percentage points, enabling better support for model-based testing. These results demonstrate that EdgeFlow provides a practical, training-free means to improve topology-preserving flowchart-to-Mermaid conversion for industrial RE. Cross-dataset evaluation results on a public synthetic benchmark show no significant improvement; this highlights the need for diverse benchmarks incorporating industrial data for the comprehensive evaluation of future VLM-based RE tools.

Zhifei Dou, Shabnam Hassani, Ou Wei

Huawei Research Canada

Industrial Edge Topology

Ask PDF