[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83697-en":3,"doc-seo-83697-105":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},83697,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Agentic Orchestration of HPC Applications in Cloud","Large Language Models (LLMs) are transforming research practices by enabling autonomous, goal-oriented systems that can support staff scientists, software engineers, and administrators. The shift requires new architectural approaches and a clear understanding of LLM capabilities and limits. This work designs agents that execute the full cloud lifecycle of an HPC application run, including container creation and build, Kubernetes deployment, optimization, and orchestration of scaling studies. Results cover four established HPC applications with multi-platform images and optimization across 21 Kubernetes instance types.","Agentic Orchestration of HPC Applications in Cloud  \nVanessa Sochat∗ [sochat1@llnl.gov](sochat1@llnl.gov)  \nLawrence Livermore National Laboratory Livermore, California, USA  \nDaniel Milroy  \n[milroy1@llnl.gov](milroy1@llnl.gov)[ ](milroy1@llnl.gov)Lawrence Livermore National Laboratory  \nLivermore, California, USA  \narXiv :2607 .02925v 1 [ cs .DC] 3 Jul 2026  \nAbstract  \nLarge Language Models (LLMs) are serving as a catalyst of change for research practices, touching the daily lives of staff scientists, software engineers, and system administrators. The developments promise new degrees of autonomy, where categories of human work and decision making are replaced by autonomous, goal-oriented systems. This transition necessitates novel architectural paradigmsand solid understanding of the strengths and limitations of LLMs. In this work, we design agents to intelligently deliver the entire lifecycle of an HPC application experimental run in cloud – creation and build of a container, deployment in Kubernetes, optimization, and orchestration of a scaling study. We pursue this task for four well-known HPC applications to build multi-platform images and optimize across 21 instance types in Kubernetes. We demonstrate successful linear scaling with patterns approved by human experts, designs that improve work time to completion, and review suggested best practices for agentic design and collaboration.  \n1 Introduction  \nThe revolution of Large Language Models (LLM) for usage in artificial intelligence (AI) and machine learning (ML) workloads has taken the global research community by storm. The high performance computing (HPC) community is a representative subset of this user base that can benefit from using AI/ML models to advance science. The interfaces to interact with LLMs are typically agents – applications that can receive instructions and respond with context-aware, meaningful text in coordination with AI services [7] . Successful integration of agents into scientific workflows depends on understanding strengths and limitations, and strategy to holistically combine human goals with LLM productivity. A LLM is only as powerful as its ability to focus on a scoped task, and an agentic team of LLMs and humans will best achieve a desired outcome with proper protocol for guidance and validation. As natural language becomes a part of a new type of software to create revolutionary new systems, the feedback loop between agents and humans must become tighter [5] .  \nA variety of developer frameworks [11, 19] and hosted services are available for inference, including Google’s Gemini, Anthropic’s Claude, OpenAI’s ChatGPT, and Microsoft Copilot. These AI systems are being used in medicine, education, and science [15, 16, 29] . They are designed to derive objectives from prompts, and synthesize multiple data sources while using internal tools to plan, reason, and execute complex, multi-step tasks. While the structure is not typically transparent to the user, we can speculate that these systems have checks and balances, can adapt to failure, and use a mixture of experts (MOE) [9] to target sub-tasks to models with tuned expertise. Although a response to the user may appear as  \n∗ Corresponding Author  \na single, cohesive output, it likely results from synthesis of multiple sources of information and multiple steps, each with support from tools. Tools might include symbolic solvers for formal logic, code interpreters to produce accurate mathematical results, and search engines or databases for general knowledge retrieval. A planner that initially processes the prompt is likely responsible for orchestrating agents and tools into an execution pipeline. Industry vendors are ahead of the game to structure these interactions, developing the Model Context Protocol (MCP) to standardize AI system interactions [22] .  \nWhile corporations can afford and utilize these services, scientific groups are more cost constrained and can be limited by institutional","cbCaieM5a1UwPXnK","https://ap.wps.com/l/cbCaieM5a1UwPXnK","pdf",1520539,3,1,11,"English","en",105,"# Introduction\n## Agentic AI for Computational Science","[{\"question\":\"What problem does the document address for HPC research workflows?\",\"answer\":\"It targets how LLM-driven agents can deliver end-to-end autonomy for HPC application runs in cloud environments, including build, deployment, optimization, and scaling orchestration.\"},{\"question\":\"How are the agents used in the lifecycle of an HPC application run?\",\"answer\":\"They handle container creation and build, deploy workloads on Kubernetes, optimize execution, and orchestrate scaling studies in a coordinated agentic workflow.\"},{\"question\":\"Which HPC applications and infrastructure scope are evaluated?\",\"answer\":\"The document evaluates four well-known HPC applications, generating multi-platform images and optimizing across 21 Kubernetes instance types to demonstrate scaling behavior and efficiency improvements.\"}]",1784189805,28,{"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},"agentic-orchestration-of-hpc-applications-in-cloud","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/agentic-orchestration-of-hpc-applications-in-cloud/83697/",4,{"url":51,"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},"What problem does the document address for HPC research workflows?","Question",{"text":75,"@type":76},"It targets how LLM-driven agents can deliver end-to-end autonomy for HPC application runs in cloud environments, including build, deployment, optimization, and scaling orchestration.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the agents used in the lifecycle of an HPC application run?",{"text":80,"@type":76},"They handle container creation and build, deploy workloads on Kubernetes, optimize execution, and orchestrate scaling studies in a coordinated agentic workflow.",{"name":82,"@type":73,"acceptedAnswer":83},"Which HPC applications and infrastructure scope are evaluated?",{"text":84,"@type":76},"The document evaluates four well-known HPC applications, generating multi-platform images and optimizing across 21 Kubernetes instance types to demonstrate scaling behavior and efficiency improvements.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"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":52,"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"]