[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81631-en":3,"doc-seo-81631-105":30,"detail-sidebar-cat-0-en-105":91},{"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":13,"seo_description":14,"update_tm":28,"read_time":29},81631,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","A Self-Evolving Agentic Framework for Metasurface Inverse Design","Metasurface inverse design can realize complex optical functionality, yet translating a target optical response into runnable optimization code usually demands deep computational electromagnetics expertise and solver-specific engineering. A self-evolving agentic framework reduces this barrier by coupling a coding agent, explicit human-readable skill files, and a deterministic physics-based evaluator. Instead of updating model weights, skill files are revised from solver-grounded feedback while the base model and differentiable solver remain fixed. Benchmarks show improved success, higher physical-criteria satisfaction, and fewer attempts, with strong transfer to new task families.","arXiv :2604 .0 1480v2 [ cs .AI] 10 Jul 2026  \nA SELF-EVOLVING AGENTIC FRAMEWORK FOR METASURFACE  \nINVERSE DESIGN  \nYi Huang  *,1 , Bowen Zheng 1 , Yunxi Dong 1 , Hong Tang 1 , Huan Zhao 1 , S. M. Rakibul Hasan Shawon 1 , and  \nHualiang Zhang,\\#,1  \n1Department of Electrical and Computer Engineering, University of Massachusetts Lowell  \n*[Yi_Huang@student.uml.edu](Yi_Huang@student.uml.edu),\\#[Hualiang_Zhang@uml.edu](Hualiang_Zhang@uml.edu)  \nABSTRACT  \nMetasurface inverse design can realize complex optical functionality, but turning a target optical response into executable optimization code still requires substantial expertise in computational electromagnetics and solver-specific software engineering. We present a self-evolving agentic framework that lowers this barrier by coupling a coding agent, explicit human-readable skill files, and a deterministic physics-based evaluator. Rather than updating model weights, it revises the skill files from solver-grounded feedback, while the base model and differentiable solver, which provides the physics simulation and gradients, stay fixed. On a multi-type benchmark, skill evolution raises same-type task success from 38% to 74%, the fraction of physical criteria met from 0.51 to 0.87, and reduces average attempts from 4.10 to 2.30 . On two new-type families, success holds near ceiling on one (0.92 to 0.90) and rises from 0.20 to 0.90 on the other. Skill evolution offers a practical path toward autonomous and accessible inverse-design workflows.  \nKeywords metasurface inverse design · self-evolving agents · agentic workflow · skill evolution · large language model (LLM) · differentiable electromagnetic solver  \n1 Introduction  \nMetasurface design is increasingly cast as an inverse problem, in which a target optical response is specified and the corresponding structure is sought [1, 2] . This paradigm reflects the growing demand for broadband, multifunctional, and highly integrated meta-optical devices, whose design spaces are high-dimensional, strongly coupled, and resistant to intuition-guided exploration, particularly under freeform parameterizations [3–8] . In parallel, deep-learning-assisted methods have broadened the computational design landscape for metasurfaces and flat optics [9–11] . As a result, manual geometry tuning and parameter sweeps no longer suffice to identify high-performance structures, and computational inverse-design has become central to metasurface research [1, 2, 6, 8, 12, 13] . Yet this growing centrality has not translated into commensurate ease of automation: converting a desired optical response into a working design program still requires specialized knowledge of computational electromagnetics together with the solver-specific software engineering needed to implement and maintain it [2, 6] . These barriers often confine inverse design to relatively narrow, task-specific design problems that are difficult to extend to more complex functionalities or to the broader multiphysics applications that interdisciplinary research requires.  \nConcretely, the researcher must select a parameterization, define the objective and constraints, decide how to initialize and optimize the variables, and verify the solver outputs [2, 6] . Recent progress in large language model (LLM)-based coding, tool use, and natural-language interaction makes part of this workflow easier. Early studies in nanophotonic inverse design mostly used LLMs as surrogate predictors or natural-language interfaces to existing tasks [14–17] . More recent systems instead use the model to write code, call tools, and assemble optimization loops around established computational engines [18, 19] . Our recent Model Context Protocol (MCP)-based framework showed that this workflow can be grounded in standardized solver access without compromising mathematical rigor [20] . Even so, these systems can complete a task-specific workflow but do not retain solver-specific tactics in a form that later tasks can reuse [1","cbCaifUbq3dfX6U1","https://ap.wps.com/l/cbCaifUbq3dfX6U1","pdf",7896952,4,1,21,"English","en",105,"# Introduction\n# Methods\n## Framework Overview\n## Evaluation Protocol\n# Results\n## Task Success and Efficiency\n## Error Patterns and Agent Behavior\n## Cost and Transfer\n# Discussion\n## Implications and Limits","[{\"question\":\"How does the proposed framework evolve the agent’s capabilities during optimization?\",\"answer\":\"It revises explicit, human-readable skill files based on solver-grounded feedback. The base model weights are kept fixed.\"},{\"question\":\"What role does the differentiable electromagnetic solver play?\",\"answer\":\"The fixed differentiable solver performs physics simulation and provides gradients for evaluating and searching candidate metasurface designs.\"},{\"question\":\"What improvements are reported on benchmarks and for new task families?\",\"answer\":\"Skill evolution increases same-type task success and the fraction of physical criteria met while reducing average attempts. It also achieves near-ceiling performance on one new-type family and a large success gain on another.\"}]",1784174977,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-self-evolving-agentic-framework-for-metasurface-inverse-design","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/a-self-evolving-agentic-framework-for-metasurface-inverse-design/81631/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the proposed framework evolve the agent’s capabilities during optimization?","Question",{"text":75,"@type":76},"It revises explicit, human-readable skill files based on solver-grounded feedback. The base model weights are kept fixed.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What role does the differentiable electromagnetic solver play?",{"text":80,"@type":76},"The fixed differentiable solver performs physics simulation and provides gradients for evaluating and searching candidate metasurface designs.",{"name":82,"@type":73,"acceptedAnswer":83},"What improvements are reported on benchmarks and for new task families?",{"text":84,"@type":76},"Skill evolution increases same-type task success and the fraction of physical criteria met while reducing average attempts. It also achieves near-ceiling performance on one new-type family and a large success gain on another.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]