[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81834-en":3,"doc-seo-81834-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},81834,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","TO-Master: an LLM-agent framework for automated topology optimization","Topology optimization (TO) is a mature computational design method, yet it still demands extensive manual work in geometry preparation, mesh generation, boundary-condition assignment, solver setup, and postprocessing, which limits adoption beyond expert workflows. TO-Master introduces an LLM-agent framework that converts finite-element-based TO into a conversational, tool-orchestrated process. From natural-language instructions and optional mesh/geometry/image inputs, it selects tools, builds validated finite element TO models, and runs sensitivity-based optimization with typed solver arguments. Experiments validate benchmark accuracy and enable complex engineering cases with optimized results, field distributions, and convergence histories, without user-written code.","arXiv :2607 .0 18 12v 1 [ cs .CE] 2 Jul 2026  \nTO-Master: an LLM-agent framework for automated  \ntopology optimization  \nHaoju Lin 1 , Wenchang Zhang 1 , Weipeng Xu 1 , Xiang Li2 , Tian Xu 1*,  \nTianju Xue 1*  \n1 Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, China.  \n2 China Iron and Steel Research Institute Group, Beijing, China.  \n*Corresponding author(s). E-mail(s): [tianxu@ust.hk](tianxu@ust.hk) ; [cetxue@ust.hk](cetxue@ust.hk) ;  \nAbstract  \nTopology optimization (TO) has become a mature computational design method, but using it still requires substantial manual effort in geometry preparation, mesh generation, boundary-condition assignment, solver setup, and postprocessing. This implementation barrier limits the use of TO outside expert workflows, even when differentiable finite element solvers are available. This work introduces TO-Master, a large language model (LLM) agent framework that turns finite-element-based TO into a conversational, toolorchestrated workflow. From natural language instructions and optional mesh, geometry, or image inputs, the agent selects computational tools, constructs finite element TO models, checks meshes and boundary conditions, and launches sensitivity-based optimization with typed solver arguments. The framework supports generated and uploaded meshes, image-to-mesh conversion, 2D and 3D structural compliance minimization, thermal conduction, multiple load cases, stress-constrained optimization, and engineering geometries.  \nNumerical experiments show that TO-Master can reproduce standard benchmark results and solve more complex engineering examples while returning optimized results, field distributions, convergence histories, and interactive artifacts without user-written code. An instruction ablation study further shows that tool-usage rules, internal reasoning guidance, and few-shot examples are critical for robust formulation under ambiguous user input. By combining LLM-agent orchestration with deterministic finite element and optimization tools, TO-Master removes the burden of trivial setup and routine model construction, lowers the modeling barrier of TO, and preserves a reliable numerical workflow. The TO-Master platform is available online at [https://www.bohrium.com/en/apps/to-master](https://www.bohrium.com/en/apps/to-master).  \nKeywords: Topology optimization, LLM agent, Natural-language-driven modeling,  \nAutomated model generation  \n1 Introduction  \nTopology optimization (TO) is a computational design method that optimizes the material distribution in a prescribed design domain subject to boundary conditions, constraints, and objective functions. Classical methods include the homogenization-based method [1], the solid isotropic material with penalization (SIMP) method [2–4], the level-set method [5, 6], and the bi-directional evolutionary structural optimization method [7, 8] . These methods have been widely used for structural design, thermal design, and multi-physics inverse design problems. However, setting up a TO problem remains a nontrivial task. Users must specify  \ngeometries, meshes, boundary conditions, material models, objectives, constraints, optimization parameters, and post-processing procedures. This process usually requires substantial problem-specific scripting and repeated manual modification, which limits the accessibility of TO workflows.  \nRecent advances in differentiable programming and automatic differentiation provide new opportunities for computational mechanics and inverse design. Automatic-differentiationbased TO frameworks such as AuTO [9] or differentiable finite element method (FEM) frameworks such as JAX-FEM [10] shows that finite element assembly, solution procedures, and objective evaluations can be embedded in automatic-differentiation-compatible computational graphs, making it possible to obtain sensitivities through automatic differentiation. These developments reduce the i","cbCaiaOYCOEZPr9K","https://ap.wps.com/l/cbCaiaOYCOEZPr9K","pdf",5171874,4,1,29,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does TO-Master address in topology optimization workflows?\",\"answer\":\"TO-Master targets the heavy manual setup required in TO, including geometry preparation, mesh generation, boundary-condition assignment, solver configuration, and postprocessing, which creates an implementation barrier for non-expert use.\"},{\"question\":\"How does TO-Master use an LLM agent to perform topology optimization?\",\"answer\":\"The agent takes natural-language instructions and optional mesh, geometry, or image inputs, selects appropriate computational tools, constructs finite element TO models, checks meshes and boundary conditions, and launches sensitivity-based optimization using typed solver arguments.\"},{\"question\":\"What capabilities are supported by the TO-Master framework?\",\"answer\":\"TO-Master supports generated and uploaded meshes, image-to-mesh conversion, 2D and 3D structural compliance minimization, thermal conduction, multiple load cases, stress-constrained optimization, and engineering geometries.\"}]","TO-Master: an LLM-agent framework for automated topology optimization | PDF",1784176518,73,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"to-master-an-llm-agent-framework-for-automated-topology-optimization","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/to-master-an-llm-agent-framework-for-automated-topology-optimization/81834/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-29","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does TO-Master address in topology optimization workflows?","Question",{"text":76,"@type":77},"TO-Master targets the heavy manual setup required in TO, including geometry preparation, mesh generation, boundary-condition assignment, solver configuration, and postprocessing, which creates an implementation barrier for non-expert use.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does TO-Master use an LLM agent to perform topology optimization?",{"text":81,"@type":77},"The agent takes natural-language instructions and optional mesh, geometry, or image inputs, selects appropriate computational tools, constructs finite element TO models, checks meshes and boundary conditions, and launches sensitivity-based optimization using typed solver arguments.",{"name":83,"@type":74,"acceptedAnswer":84},"What capabilities are supported by the TO-Master framework?",{"text":85,"@type":77},"TO-Master supports generated and uploaded meshes, image-to-mesh conversion, 2D and 3D structural compliance minimization, thermal conduction, multiple load cases, stress-constrained optimization, and engineering geometries.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]