[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-503874-105":59,"doc-detail-503874-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","casper-change-aware-slice-prioritization-for-efficient-regression-testing-of-llm-based-systems","CASPER - Change-Aware Slice Prioritization for Efficient Regression Testing of LLM-based systems","","Regression testing for LLM-based systems is difficult because failures in individual instances often do not reveal system-level faults, while changes in overall performance are too coarse to pinpoint affected behaviors. The paper proposes CASPER, a change-aware slice prioritization framework that analyzes regression instances at an intermediate granularity via test suite slices. CASPER identifies regression slices with consistent semantic and performance characteristics and prioritizes them using behavioral evidence from execution logs. Experiments in software issue resolution show improved slice consistency and better prioritization across changes and testing budgets.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":30,"@type":76,"position":81},"https://docshare.wps.com/document/technology/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/casper-change-aware-slice-prioritization-for-efficient-regression-testing-of-llm-based-systems/503874/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/casper-change-aware-slice-prioritization-for-efficient-regression-testing-of-llm-based-systems/503874.png","ImageObject",300,407,{"name":92,"@type":93},"Guten Appetit_Joghurt","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-10-03",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is traditional regression testing insufficient for LLM-based systems?","Question",{"text":112,"@type":113},"A single regression failure may not indicate a meaningful system regression or provide enough information to diagnose affected behaviors. Relying only on overall performance changes is too coarse to identify which behaviors are impacted.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What does CASPER do to improve regression testing efficiency?",{"text":117,"@type":113},"CASPER analyzes regression instances through intermediate-level test suite slices. It identifies regression slices with semantically related instances and consistent performance, then prioritizes slices based on the likelihood of regression using behavioral data from execution logs.",{"name":119,"@type":110,"acceptedAnswer":120},"How was CASPER evaluated and what were the results?",{"text":121,"@type":113},"The framework was instantiated in the software issue resolution domain. Slice identification was compared to clustering-based baselines, and slice prioritization was compared to a random ranking baseline, showing more consistent slices and improved prioritization across different LLM-based changes and testing budgets.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},503874,1791100631,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},1374408768420,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","arXiv :2608 .00378v 1 [ cs . SE] 1 Aug 2026  \nCASPER — Change-Aware Slice Prioritization for Efficient Regression Testing of LLM-based systems  \nBIRUK ASMARE MUSE✉ , School ofEECS, University of Ottawa, Canada LIONEL BRIAND✉ , School ofEECS, University of Ottawa, Canada YIWEI LU✉ , School ofEECS, University of Ottawa, Canada  \nKEHELIYA GALLABA✉ , Centre for Software Excellence, Huawei Canada, Canada  \nRegression testing for LLM-based systems poses unique challenges because individual regression instances provide limited information about system-level regressions. A failure in a single instance does not necessarily indicate a meaningful regression or provide sufficient information to diagnose affected behaviors. Conversely, detecting regressions based only on overall system performance changes is too coarse-grained, as it does not identify which behaviors are affected. This motivates analyzing regression instances at an intermediate level through test suite slices.  \nTo address this challenge, we propose CASPER, a change-aware slice prioritization framework for efficient regression testing of prompt-level and model-level changes in LLM-based systems. CASPER first identifies regression slices containing semantically related instances with consistent performance characteristics using an evolutionary slice identification approach. Given a change to an LLM-based application, CASPER prioritizes slices according to their likelihood of regression using behavioral information extracted from execution logs. We instantiate CASPER in the software issue resolution domain and evaluate slice identification against clustering-based baselines and regressed slice prioritization against a random ranking baseline. Results show that CASPER generates more consistent slices while maintaining comparable or better semantic coherence and improves regressed slice prioritization across different LLM-based system changes and testing budgets.  \nCCS Concepts: • Software and its engineering → Software testing and debugging.  \nAdditional Key Words and Phrases: Regression testing, LLM-based systems, slice prioritization, slice identification, evolutionary search  \nACM Reference Format:  \nBiruk Asmare Muse, Lionel Briand, Yiwei Lu, and Keheliya Gallaba. 2018. CASPER — Change-Aware Slice Prioritization for Efficient Regression Testing of LLM-based systems. J. ACM 37, 4, Article 111 (August 2018), 45 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nIncorporating Large Language Models (LLMs) into software systems requires significant adjustments to traditional regression testing methodologies. An LLM-based system consists of an LLM integrated with a surrounding software scaffold that manages its interaction with the external environment. The scaffold executes the actions proposed by the LLM, collects the resulting observations, and feeds them back to the model, enabling iterative reasoning and action toward accomplishing a given task.  \nAuthors’ Contact Information: Biruk Asmare Muse, [bmuse@uottawa.ca](bmuse@uottawa.ca), School ofEECS, University of Ottawa, Ottawa, Ontario, Canada; Lionel Briand, [lbriand@uottawa.ca](lbriand@uottawa.ca), School ofEECS, University of Ottawa, Ottawa, Ontario, Canada; Yiwei Lu, [yiwei.lu@uottawa.ca](yiwei.lu@uottawa.ca), School ofEECS, University of Ottawa, Ottawa, Ontario, Canada; Keheliya Gallaba, [gallabak@sigsoft.org](gallabak@sigsoft.org), Centre for Software Excellence, Huawei Canada, ON, Canada.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, [re","cbCails6cfja7KTb","https://ap.wps.com/l/cbCails6cfja7KTb","pdf",911587,45,"English","# Introduction\n## Regression testing challenges for LLM-based systems\n## Proposed approach: CASPER and slice prioritization\n## Evaluation methodology and results","[{\"question\":\"Why is traditional regression testing insufficient for LLM-based systems?\",\"answer\":\"A single regression failure may not indicate a meaningful system regression or provide enough information to diagnose affected behaviors. Relying only on overall performance changes is too coarse to identify which behaviors are impacted.\"},{\"question\":\"What does CASPER do to improve regression testing efficiency?\",\"answer\":\"CASPER analyzes regression instances through intermediate-level test suite slices. It identifies regression slices with semantically related instances and consistent performance, then prioritizes slices based on the likelihood of regression using behavioral data from execution logs.\"},{\"question\":\"How was CASPER evaluated and what were the results?\",\"answer\":\"The framework was instantiated in the software issue resolution domain. Slice identification was compared to clustering-based baselines, and slice prioritization was compared to a random ranking baseline, showing more consistent slices and improved prioritization across different LLM-based changes and testing budgets.\"}]","CASPER - Change-Aware Slice Prioritization for Efficient Regression Testing of LLM-based systems | PDF",1791061308,113]