[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82887-en":3,"doc-seo-82887-105":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},82887,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Understanding Student Perceptions Mistakes and Debugging Approaches when Solving Natural Language Programming Tasks","Learning to work with code-generating AI models is an important capability for novice programmers, and Prompt Problems is one teaching approach that uses natural-language prompts to produce solution code. A CS1 study examined over 900 students’ attempts to solve dialogue-based Prompt Problems by analyzing student reflections, unsuccessful prompts, and described debugging strategies. Students generally perceived prompting tasks as easier, more enjoyable, and better aligned with problem-solving skill development. Common errors came from omitting key details, with recovery focused on clarifying intent and revisiting task information rather than inspecting generated code or tests.","Understanding Student Perceptions, Mistakes, and Debugging Approaches when Solving Natural Language Programming Tasks  \narXiv :2607 .05034v 1 [ cs .CY] 6 Jul 2026  \nVictor-Alexandru Pădurean  \nMPI-SWS Saarbrücken, Germany [vpadurea@mpi-sws.org](vpadurea@mpi-sws.org)  \nMusa Blake  \nAbilene Christian University Abilene, TX, USA [mbb23c@acu.edu](mbb23c@acu.edu)  \nJuho Leinonen  \nAalto University Espoo, Finland [juho.2.leinonen@aalto.fi](juho.2.leinonen@aalto.fi)  \nKaitlin Riegel  \nUniversity of Auckland Auckland, New Zealand [kaitlin.riegel@auckland.ac.nz](kaitlin.riegel@auckland.ac.nz)  \nPaul Denny University of Auckland Auckland, New Zealand [paul@cs.auckland.ac.nz](paul@cs.auckland.ac.nz)  \nStephen MacNeil  \nTemple University Philadelphia, PA, USA [stephen.macneil@temple.edu](stephen.macneil@temple.edu)  \nGweneth Barbre  \nAbilene Christian University Abilene, TX, USA [gab23c@acu.edu](gab23c@acu.edu)  \nAlkis Gotovos  \nMPI-SWS Saarbrücken, Germany [agkotovo@mpi-sws.org](agkotovo@mpi-sws.org)  \nJames Prather  \nAbilene Christian University Abilene, TX, USA [james.prather@acu.edu](james.prather@acu.edu)  \nAdish Singla  \nMPI-SWS Saarbrücken, Germany [adishs@mpi-sws.org](adishs@mpi-sws.org)  \nAbstract  \nLearning to communicate with code-generating AI models is an emerging skill for novice programmers. One recent pedagogical approach, Prompt Problems, has students solve computational tasks by writing natural-language prompts for code-generating AI models. However, little is known about the specific prompt-level mistakes novice programmers make, the kinds of computational details they fail to communicate, and what strategies they use to recover when generated code is incorrect. In a CS1 course, we studied attempts by more than 900 students to solve dialogue-based Prompt Problems. We analyzed student reflections, unsuccessful prompts, and reported debugging strategies. Compared to traditional coding tasks, students generally found prompting easier, more enjoyable, and better targeted at developing problem-solving skills. The most common mistakes are related to the omission of key details, suggesting both a failure to acknowledge their importance and over-reliance on AI to infer them. When prompts failed, students focused more on clarifying their intent and reflecting on the provided problem details than on tracing generated code or examining test cases.  \nCCS Concepts  \n• Social and professional topics → Computing education; • Computing methodologies → Artificial intelligence.  \nICER 2026 Vol. 1, Uppsala, Sweden  \n© 2026 Copyright held by the owner/author(s) .  \nThis is the author’s version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the ACM Conference on International Computing Education Research Vol.1 (ICER 2026 Vol. 1), August 11–14, 2026, Uppsala, Sweden, [https://doi.org/10.1145/3765964.3811639](https://doi.org/10.1145/3765964.3811639) .  \nKeywords  \nnatural language programming, code-generating AI, Prompt Problems, student perceptions  \nACM Reference Format:  \nVictor-Alexandru Pădurean, Kaitlin Riegel, Gweneth Barbre, Musa Blake, Paul Denny, Alkis Gotovos, Juho Leinonen, Stephen MacNeil, James Prather, and Adish Singla. 2026. Understanding Student Perceptions, Mistakes, and Debugging Approaches when Solving Natural Language Programming Tasks. In Proceedings of the ACM Conference on International Computing Education Research Vol.1 (ICER 2026 Vol. 1), August 11–14, 2026, Uppsala, Sweden. ACM, New York, NY, USA, 16 pages. [https://doi.org/10.1145/3765964](https://doi.org/10.1145/3765964) . 3811639  \n1 Introduction  \nThe skills required by computing professionals are evolving as AI becomes increasingly integrated into the software development process [11, 19, 85] . Generative AI (GenAI) is reshaping how software is created, tested, and maintained, and introducing new modes of interaction between humans and AI systems [81] . These include","cbCaimaTiQV4zXiK","https://ap.wps.com/l/cbCaimaTiQV4zXiK","pdf",1178737,4,1,16,"English","en",105,"# Introduction\n# Learning with Code-Generating AI and Prompting Skills\n## Prompt Problems in CS1\n## Study Focus and Research Questions\n# Findings: Mistakes and Debugging Strategies\n## Common Prompt-Level Mistakes\n## Recovery Strategies When Code Is Incorrect\n# Implications for Introductory Computing Education","[{\"question\":\"What is the Prompt Problems approach in natural language programming tasks?\",\"answer\":\"Prompt Problems presents students with a computational task (via a visual representation) and requires them to write a natural-language prompt to generate solution code. The interaction emphasizes prompt writing as part of solving programming tasks.\"},{\"question\":\"What kinds of prompt-level mistakes are most common for novice students?\",\"answer\":\"The most common mistakes involve omitting key details. This suggests students may not recognize the importance of certain computational information and may rely on the AI to infer missing parts.\"},{\"question\":\"When generated code is incorrect, what strategies do students use to debug?\",\"answer\":\"Students focus on clarifying their intent and reflecting on the provided problem details. Compared with traditional debugging, they are less likely to trace generated code or examine test cases when prompts fail.\"}]",1784183708,40,{"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},"understanding-student-perceptions-mistakes-and-debugging-approaches-when-solving-natural-language-programming-tasks","",{"@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/understanding-student-perceptions-mistakes-and-debugging-approaches-when-solving-natural-language-programming-tasks/82887/",{"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","2026-07-22","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 is the Prompt Problems approach in natural language programming tasks?","Question",{"text":75,"@type":76},"Prompt Problems presents students with a computational task (via a visual representation) and requires them to write a natural-language prompt to generate solution code. The interaction emphasizes prompt writing as part of solving programming tasks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What kinds of prompt-level mistakes are most common for novice students?",{"text":80,"@type":76},"The most common mistakes involve omitting key details. This suggests students may not recognize the importance of certain computational information and may rely on the AI to infer missing parts.",{"name":82,"@type":73,"acceptedAnswer":83},"When generated code is incorrect, what strategies do students use to debug?",{"text":84,"@type":76},"Students focus on clarifying their intent and reflecting on the provided problem details. Compared with traditional debugging, they are less likely to trace generated code or examine test cases when prompts fail.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]