[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-565328-105":3,"detail-sidebar-cat-1-en-105":81,"doc-detail-565328-en":126},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","genai-drawio-creator-a-framework-for-automated-diagram-generation","GenAI-DrawIO-Creator - A Framework for Automated Diagram Generation","","Diagrams are essential for communicating complex information, yet generating and editing them is often slow and tool-dependent. GenAI-DrawIO-Creator is an LLM-based framework that converts natural-language descriptions into fully editable draw.io diagrams by producing valid, well-formed XML. The system integrates Claude 3.7 for structured visual reasoning, with prompt engineering and error-checking for correctness. A prototype generates and replicates diagrams with strong structural fidelity, reducing creation time.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/template/","Template",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/template/presentations/","Presentations",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/template/genai-drawio-creator-a-framework-for-automated-diagram-generation/565328/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/genai-drawio-creator-a-framework-for-automated-diagram-generation/565328.png","ImageObject",442,249,{"name":42,"@type":43},"pop out","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-22","2026-10-13",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does GenAI-DrawIO-Creator address?","Question",{"text":63,"@type":64},"It targets the labor-intensive process of creating and modifying diagrams, which often requires manual effort and specialized tools.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the framework produce editable diagrams for draw.io?",{"text":68,"@type":64},"It uses Claude 3.7 to translate user intents into the structured XML format required by draw.io, applying prompting and XML post-processing to maintain correctness.",{"name":70,"@type":61,"acceptedAnswer":71},"What capabilities and evaluation outcomes are reported?",{"text":72,"@type":64},"The prototype generates accurate diagrams from natural language or code, can replicate diagrams from images, and simulated evaluations show reduced creation time with high structural fidelity.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},565328,1792403908,{"code":4,"msg":82,"data":83},"success",[84,88,93,98,103,108,113,118,122],{"id":85,"doc_module":22,"doc_module_name":25,"category_name":29,"show_sort_weight":86,"slug":87},11,90,"presentations",{"id":89,"doc_module":22,"doc_module_name":25,"category_name":90,"show_sort_weight":91,"slug":92},12,"Resumes",80,"resumes",{"id":94,"doc_module":22,"doc_module_name":25,"category_name":95,"show_sort_weight":96,"slug":97},14,"Invoices",70,"invoices",{"id":99,"doc_module":22,"doc_module_name":25,"category_name":100,"show_sort_weight":101,"slug":102},15,"Posters",60,"posters",{"id":104,"doc_module":22,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},16,"Social Media",50,"social-media",{"id":109,"doc_module":22,"doc_module_name":25,"category_name":110,"show_sort_weight":111,"slug":112},17,"Forms",40,"forms",{"id":114,"doc_module":22,"doc_module_name":25,"category_name":115,"show_sort_weight":116,"slug":117},18,"Letters",30,"letters",{"id":119,"doc_module":22,"doc_module_name":25,"category_name":120,"show_sort_weight":55,"slug":121},21,"Paper Templates","papers-templates",{"id":123,"doc_module":22,"doc_module_name":25,"category_name":124,"show_sort_weight":4,"slug":125},158,"General","general-158",{"code":4,"msg":82,"data":127},{"doc_id":79,"user_id":128,"nickname":42,"user_avatar":129,"doc_module":22,"category_id":85,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":130,"file_id":131,"file_url":132,"file_type":133,"file_size":134,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":55,"language":135,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":136,"faqs":137,"seo_title":138,"seo_description":12,"update_tm":139,"read_time":26},962090760408,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","arXiv :2601 .05162v2 [ cs .GR] 23 Mar 2026  \nGenAI-DrawIO-Creator: A Framework for Automated Diagram  \nGeneration  \nJinze Yu, Dayuan Jiang  \nFigure 1: Overview of GenAI-DrawIO-Creator: A system that transforms natural language descriptions into fully editable diagrams using Claude 3.7 to generate draw.io compatible XML.  \nAbstract  \nDiagrams are crucial for communicating complex information, yet creating and modifying them remains a labor-intensive task. We present GenAI-DrawIO-Creator, a novel framework that leverages Large Language Models (LLMs) to automate diagram generation and manipulation in the structured XML format used by draw.io. Our system integrates Claude 3.7 to reason about structured visual data and produce valid diagram representations. Key contributions include a high-level system design enabling real-time diagram updates, specialized prompt engineering and error-checking to ensure well-formed XML outputs. We demonstrate a working prototype capable of generating accurate diagrams (such as network architectures and flowcharts) from natural language or code, and even replicating diagrams from images. Simulated evaluations show that our approach significantly reduces diagram creation time and produces outputs with high structural fidelity. Our results highlight the promise of Claude 3.7 in handling structured visual reasoning tasks and lay the groundwork for future research in AI-assisted diagramming applications.  \n1 Introduction  \nDiagrams (e.g., flowcharts, architectural schematics) play a vital role in knowledge representation, allowing complex relationships to be understood at a glance. However, creating these diagrams typically requires manual effort and proficiency with specialized tools. This  \nposes challenges in fast-paced or collaborative environments where rapid iteration and easy updates are needed.  \nExisting automatic diagram-generation solutions are limited: many infrastructure-as-code tools can output architecture diagrams, but often only as static images (PDF/PNG) that are difficult to edit or extend. The ideal solution would allow users to describe a diagram in natural language (or provide structured input like code) and receive an editable diagram that can be refined as needed.  \nRecent advances in generative AI suggest that Large Language Models (LLMs) could bridge this gap. LLMs have shown the ability to interpret complex instructions and generate structured outputs such as code or JSON [3, 6, 10] . This opens up the possibility of LLM-driven diagram creation: a user could simply describe the desired diagram, and an LLM could generate the corresponding diagram file.  \nImplementing LLM-based diagram generation introduces several technical challenges:  \nThe model must output well-structured diagram data (e.g., XML) without errors; free-form text generation easily leads to syntax mistakes or hallucinated content that breaks the diagram [7, 13] .  \nControlling the content of the diagram requires the LLM to reason about the spatial and relational arrangement of elements described in text. Ensuring the reliability and consistency of structured outputs from an LLM requires careful prompting and validation techniques [2, 12] .  \nIn this paper, we introduce GenAI-DrawIO-Creator, an LLM framework designed to automatically generate and manipulate diagrams through natural language interactions.1 . Our system is built with a high-level architecture that integrates Anthropic’s Claude 3.7 and a web-based diagramming interface. The core idea is to use Claude to translate user intents into the structured format of a draw.io diagram, while maintaining an interactive loop where the user can refine the diagram through dialogue.  \nThe contributions of this work are summarized as follows:  \n• We propose a novel LLM-driven system for automated diagram generation, detailing an architecture that combines front-end visual embedding with back-end AI integration for structured data output.  \n• We develop specialized te","cbCair50fJHLqHt9","https://ap.wps.com/l/cbCair50fJHLqHt9","pdf",810687,"English","# Introduction\n## Related Work\n### Large Language Models for Structured Output\n### Diagram Generation Approaches\n### Multimodal and Interactive Approaches","[{\"question\":\"What problem does GenAI-DrawIO-Creator address?\",\"answer\":\"It targets the labor-intensive process of creating and modifying diagrams, which often requires manual effort and specialized tools.\"},{\"question\":\"How does the framework produce editable diagrams for draw.io?\",\"answer\":\"It uses Claude 3.7 to translate user intents into the structured XML format required by draw.io, applying prompting and XML post-processing to maintain correctness.\"},{\"question\":\"What capabilities and evaluation outcomes are reported?\",\"answer\":\"The prototype generates accurate diagrams from natural language or code, can replicate diagrams from images, and simulated evaluations show reduced creation time with high structural fidelity.\"}]","GenAI-DrawIO-Creator - A Framework for Automated Diagram Generation | PDF",1791851416]