[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82857-en":3,"doc-seo-82857-105":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},82857,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","An Exploration of Agentic Information Fusion for Test Maintenance Prediction","Test maintenance is a critical but expensive activity as software codebases evolve rapidly. The document presents MAST, a multiagent framework that predicts which existing test cases must be modified or deleted after changes in production code. The approach addresses the challenge of complex relations between production and test artifacts by combining static, lexical, and semantic analyses, fused through an intelligent integration and post-check procedure. Evaluation on 21 industrial Java repositories shows improved precision, F1, and F2 over a strong baseline, with ablations confirming the contribution of each analysis.","An Exploration of Agentic Information Fusion for Test  \nMaintenance Prediction  \nJingxiong Liu  \n[liujing@chalmers.se](liujing@chalmers.se)[ ](liujing@chalmers.se)Chalmers University of Technology and University of Gothenburg, Ericsson AB Gothenburg, Sweden  \nNasser Mohammadiha  \nEricsson AB Gothenburg, Sweden  \nGregory Gay  \n[greg@greggay.com](greg@greggay.com)[ ](greg@greggay.com)Chalmers University of Technology and University of Gothenburg Gothenburg, Sweden  \narXiv :2607 .04786v 1 [ cs . SE] 6 Jul 2026  \nAbstract  \nTest maintenance is a critical, yet costly, activity—particularly ascodebases rapidly evolve. To assist, we present MAST, a multiagent framework that predicts which test cases require maintenance following changes to the production code. This identification task is necessary as a precondition to any subsequent maintenance activities, but remains challenging due to the complex relationships between production and test code. MAST advances the state-of-theart by integrating multiple analyses—including static, lexical, and semantic analyses—through an intelligent fusion and post-check procedure and by focusing on a realistic use and evaluation setting—i.e., standardized input formats, repository-level analyses, and the ability to infer relations between test and production artifacts rather than assuming a pre-existing mapping.  \nWe evaluated MAST on 21 industrial Java repositories from Ericsson AB, considering situations where test maintenance both was and was not required in the ground truth. MAST yielded superior precision to a state-of-the-art baseline—resulting in a higher accuracy, F1, and F2 score—with only some loss in recall. Our ablation study demonstrates the value of each analysis in producing the final recommendations. MAST illustrates the potential of multiagent systems that can fuse multiple information sources when performing software testing tasks.  \nCCS Concepts  \n• Software and its engineering → Software testing and debugging; Software maintenance tools; • Computing methodologies → Machine learning.  \nKeywords  \nSoftware Testing, Test Maintenance, Large Language Models, MultiAgent Systems, Program Analysis  \nACM Reference Format:  \nJingxiong Liu, Nasser Mohammadiha, and Gregory Gay. 2026. An Exploration of Agentic Information Fusion for Test Maintenance Prediction.  \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, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nASE’26, Munich, Germany  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nIn Proceedings of IEEE/ACM International Conference on Automated Software Engineering (ASE’26). ACM, New York, NY, USA, 11 pages. [https:](https:)//[doi.org/XXXXXXX.XXXXXXX](doi.org/XXXXXXX.XXXXXXX)  \n1 Introduction  \nSoftware testing is a crucial, but expensive, stage in the quality assurance process [1] . Although there is an initial cost associated with creating test cases, much of the cost of testing is imposed by the ongoing need for test maintenance [32], i.e., the adaptation of the test suite as the project evolves. In most cases, such activities takes place after changes are made to the source code that render the existing test suite obsolete—i.e., some tests may no longer be necessary, some may need adaptations to match the changed behavior of the component-under-test, or new t","cbCaivT6iX9OsCzB","https://ap.wps.com/l/cbCaivT6iX9OsCzB","pdf",789654,1,11,"English","en",105,"# Introduction\n## Test localization and the role of maintenance\n## The MAST multiagent information fusion framework\n## Evaluation setup and results","[{\"question\":\"What problem does MAST address in test maintenance prediction?\",\"answer\":\"MAST identifies which test cases require modification or deletion after changes to production source code, a necessary first step before performing maintenance actions.\"},{\"question\":\"How does MAST perform test localization?\",\"answer\":\"MAST integrates multiple complementary analyses—static, lexical, and semantic—and fuses them using an intelligent fusion plus a post-check procedure to infer relationships between test and production artifacts.\"},{\"question\":\"How was MAST evaluated and what were the outcomes?\",\"answer\":\"MAST was evaluated on 21 industrial Java repositories from Ericsson AB across scenarios where test maintenance was and was not required in the ground truth, achieving better precision, higher F1 and F2 scores than a state-of-the-art baseline with some loss in recall.\"}]",1784183491,28,{"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},"an-exploration-of-agentic-information-fusion-for-test-maintenance-prediction","",{"@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/an-exploration-of-agentic-information-fusion-for-test-maintenance-prediction/82857/",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},"What problem does MAST address in test maintenance prediction?","Question",{"text":75,"@type":76},"MAST identifies which test cases require modification or deletion after changes to production source code, a necessary first step before performing maintenance actions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does MAST perform test localization?",{"text":80,"@type":76},"MAST integrates multiple complementary analyses—static, lexical, and semantic—and fuses them using an intelligent fusion plus a post-check procedure to infer relationships between test and production artifacts.",{"name":82,"@type":73,"acceptedAnswer":83},"How was MAST evaluated and what were the outcomes?",{"text":84,"@type":76},"MAST was evaluated on 21 industrial Java repositories from Ericsson AB across scenarios where test maintenance was and was not required in the ground truth, achieving better precision, higher F1 and F2 scores than a state-of-the-art baseline with some loss in recall.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]