[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85810-en":3,"doc-seo-85810-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85810,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Descriptive Execution of HPC Applications and Workflows","Execution and orchestration of software are shifting from human-written code to descriptive, intent-driven prose. In high performance computing, this evolution appears in application orchestration, workload management, and monitoring, enabled by large language models paired with tools, resources, and software-modeled functions. This work evaluates a primarily agentic framework for optimizing and running an HPC scaling study on AWS with low latency networks, translating job specs between workload managers, and executing a complete biosciences workflow.","Descriptive Execution of HPC Applications and Workflows  \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 . 10081v1 [ cs .DC] 11 Jul 2026  \nAbstract  \nThe means to execute and orchestrate software components has changed from human-written code to descriptive prose. In high performance computing, this transition is represented in application orchestration, workload management, and system monitoring and debugging, to name a few. The underlying means to enable descriptive definition of tasks is the use of Large Language Model with associated tool functions and resources. A combination of a model with access to such resources, modeled in software, encompasses an autonomous framework. As fully automated and agentic frameworks are developed for science, it is important to assess reliability and strategies scoped to specific tasks. In this work, we assess the extent to which an agentic framework can optimize and run an HPC scaling study with a low latency network in Amazon Web Services, accurately transform HPC job specifications between workload managers, and design and run an entire biosciences workflow. We find that the framework completes all three tasks while surfacing task-specific failure modes. In the scaling study, agents deploy and optimize applications but monitor running jobs inefficiently, preferring conservative fixed waits over event subscriptions. In job translation, they convert specifications between Slurm and Flux with high accuracy, with processor-affinity flags the most common error. In the bioscience workflow, the agent reproduces an expertwritten variant-calling pipeline almost exactly—agreeing with the reference call set in 18 of 19 completed runs—and reaches this result through many distinct yet functionally equivalent workflow implementations. This information is invaluable moving forward to developing multi-cluster setups with scheduling and transformation handled by agents.  \n1 Introduction  \nThe need for representation of tasks into inputs that can processed by a machine can be traced back as far as the 1890 U.S. Census, when punch cards were used to automate voting [6] . The method expanded in the 1900s to handle more tasks, from serving as library cards to proving mathematical theorems, and were foundational to modern computing today. The study of how people communicate with computers is Human-Computer Interaction (HCI) [9] and is based on the idea of mapping human intent into tasks that can be executed by a computer. Software is an attempt to materialize human understanding into operations that a computer can perform. Data captures states of phenomena that, for scientific contexts, we typically want to use to model the real world. A data format isan attempt to standardize the phenomena into structures that can best be processed by precise instructions. A modern workflow is capturing and executing a set of tasks with states, and dependencies. Even in early computing, insert of a punch card or execution of  \n∗ Corresponding Author  \ncode was a rudimentary conversation between man and machine. A successful interaction leads to a meaningful computational result that is aligned with the initial intent.  \nThe different strategies that computational scientists have adopted to use software and data to accomplish scoped tasks can be described as progressive stages. Andrej Kaparthy defines Software 1.0, 2.0, and 3.0 [13] as a transition through stages of traditional coding, neural network methods, and using Large Language Models (LLM), respectively. We might consider units of execution changing from single programs to workflows and now conversational artificial intelligence (AI) . Tasks are delegated to agents instead of programs. The 1960s through 1990s were defined by direct managemen","cbCaib6K25omJtnp","https://ap.wps.com/l/cbCaib6K25omJtnp","pdf",1003461,1,9,"English","en",105,"# Introduction\n## Representation of tasks and execution stages\n## Challenges: task representation and resource heterogeneity\n## Approach: agentic frameworks for orchestration and workflows","[{\"question\":\"How does the document describe the shift from code to descriptive execution in HPC?\",\"answer\":\"It frames execution orchestration as moving from traditional human-written programs to descriptive prose that an LLM-based agent can interpret and convert into concrete execution steps, including inputs, tasks, and environment interactions.\"},{\"question\":\"What capabilities does the agentic framework demonstrate in the reported experiments?\",\"answer\":\"The framework completes an HPC scaling study on AWS, transforms HPC job specifications between workload managers, and designs and runs an end-to-end biosciences workflow while surfacing task-specific failure modes.\"},{\"question\":\"What accuracy and correctness results are reported for job translation and the biosciences workflow?\",\"answer\":\"Job translation between Slurm and Flux is achieved with high accuracy, with processor-affinity flags as the most common error. For biosciences variant calling, the agent reproduces an expert-written pipeline almost exactly, matching the reference call set in 18 of 19 completed runs.\"}]",1784206391,23,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"descriptive-execution-of-hpc-applications-and-workflows","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/descriptive-execution-of-hpc-applications-and-workflows/85810/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 document describe the shift from code to descriptive execution in HPC?","Question",{"text":75,"@type":76},"It frames execution orchestration as moving from traditional human-written programs to descriptive prose that an LLM-based agent can interpret and convert into concrete execution steps, including inputs, tasks, and environment interactions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What capabilities does the agentic framework demonstrate in the reported experiments?",{"text":80,"@type":76},"The framework completes an HPC scaling study on AWS, transforms HPC job specifications between workload managers, and designs and runs an end-to-end biosciences workflow while surfacing task-specific failure modes.",{"name":82,"@type":73,"acceptedAnswer":83},"What accuracy and correctness results are reported for job translation and the biosciences workflow?",{"text":84,"@type":76},"Job translation between Slurm and Flux is achieved with high accuracy, with processor-affinity flags as the most common error. For biosciences variant calling, the agent reproduces an expert-written pipeline almost exactly, matching the reference call set in 18 of 19 completed runs.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]