[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83871-en":3,"doc-seo-83871-105":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},83871,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Using Process Mining to Generate AI Agents from Software Engineering Process Records","Integrating AI agents into software engineering requires specifying agents that cooperate effectively with humans in hybrid development teams. The challenge lies in choosing appropriate granularity and separating concerns: overly coarse agents become complex, while micro-agents create coordination overhead. Existing multi-agent frameworks also use rigid predefined roles and lack project-specific adaptation. The work proposes pm4aa, combining object-centric and declarative process mining over repository event logs to discover roles, generate executable agent specifications, and validate them via testing and a user study.","arXiv :2607 .04948v 1 [ cs . SE] 6 Jul 2026  \n1  \nUsing Process Mining to Generate AI Agents from Software Engineering Process Records  \nSaimir Bala 1 , Fabiana Fournier2 ,3 , Lior Limonad2 ,3 , and Andreas Metzger4  \n1 Hasso Plattner Institute (HPI), University of Potsdam, Germany [saimir.bala@hpi.de](saimir.bala@hpi.de)  \n2 IBM Software Innovation Lab (SIL), Haifa  \n[fabiana@il.ibm.com](fabiana@il.ibm.com) , [liorli@il.ibm.com](liorli@il.ibm.com)  \n3 Dept. of Information Systems, Fac. of Comp. & Inform. Science, University of Haifa  \n4 paluno Institute, University of Duisburg Essen, Essen Germany [andreas.metzger@paluno.uni-due.de](andreas.metzger@paluno.uni-due.de)  \nSummary. Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents may introduce unmanageable complexity, whereas micro-agents may create severe coordination overhead. Moreover, existing multi-agent SE frameworks typically rely on predefined role structures and do not account for project-specific characteristics or process adaptations. We address this by combining object-centric, imperative, and declarative process mining. Using event logs extracted from software repositories, our approach discovers project-specific agent roles using a predefined SE role vocabulary grounded in repository behavior and generates matching agent specifications and implementations. As proof-of-concept, we applied our approach to a well-established open-source project. We performed functional tests and an exploratory user study to determine how well the generated AI agent specifications are aligned with human expectations.  \nKey words: Process Mining, AI Agents, Software Engineering  \n1.1 Introduction  \nProcess mining turns event data into insights about how work is performed, who performs it, and under which constraints [7] . Software engineering (SE) processes are no exception: the activities of developers, reviewers, and testers leave rich event traces in version control and issue management systems, forming a largely untapped source of process knowledge. Today, SE teams are undergoing a fundamental transformation as AI agents (autonomous  \n2 Saimir Bala, Fabiana Fournier, Lior Limonad, and Andreas Metzger  \nsystems capable of decomposing goals, executing tasks, and collaborating with humans) are increasingly embedded into development workflows [21 , 2 , 19] . The SE community has already acknowledged the rise of AI teammates, and the evolution towards hybrid human-AI SE teams raises an important new engineering challenge: How to specify and realize AI agents that can effectively work alongside humans?  \nAddressing this question has several challenges. Assigning a classical SE role (such as team member in agile processes) to a single agent yields a monolithic and complex teammate that is difficult to build, test, maintain, and delegate tasks to. Conversely, defining highly fine-grained, single-task agents increases coordination overhead among agents and humans. Also, not all SE tasks may be relevant in every project, and those that are may require concrete adaptations. Formal verification may be mandatory in safety-critical systems yet irrelevant in a simple utility tool, while complex business logic may demand property-based tests beyond standard unit testing. Finally, software engineers expect agents to adhere strictly to established standards and project-specific processes [10] . Current frameworks rely on rigid, predefined canonical roles that do not adapt a project’s actual workflows [13, 21 , 11 , 14] .  \nWe address these challenges with pm4 aa, a generative pipeline that mines project-specific SE agent specifications directly from repository event data. pm4 aa treats SE processes as business processes and the activity history recorded in","cbCaii25TwkZHxEb","https://ap.wps.com/l/cbCaii25TwkZHxEb","pdf",867133,1,18,"English","en",105,"# Introduction\n## Background and Related Work\n# Method: pm4aa\n## Object-Centric Process Mining\n## Declarative Process Mining\n# Case Study and Evaluation\n## Functional Testing\n## User Study\n# Conclusion","[{\"question\":\"Why is agent granularity and separation of concerns difficult in hybrid software engineering teams?\",\"answer\":\"Assigning a classical role to one agent can lead to a monolithic teammate that is hard to build, test, maintain, and delegate. Conversely, defining very fine-grained micro-agents increases coordination overhead between agents and humans.\"},{\"question\":\"How does pm4aa derive project-specific agent roles and specifications?\",\"answer\":\"pm4aa treats version control and issue management activity as event logs, uses object-centric process mining to capture multi-object task scopes and interactions, and applies declarative process mining to extract behavioral constraints that guide agent execution.\"},{\"question\":\"How was the approach evaluated in the reported proof of concept?\",\"answer\":\"The authors implemented pm4aa with the LangGraph framework and evaluated it on the open-source Commitizen project using a case study. Evaluation included functional testing of the generated agents and a user study with ten participants assessing alignment with human expectations.\"}]",1784191118,45,{"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},"using-process-mining-to-generate-ai-agents-from-software-engineering-process-records","",{"@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/using-process-mining-to-generate-ai-agents-from-software-engineering-process-records/83871/",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},"Why is agent granularity and separation of concerns difficult in hybrid software engineering teams?","Question",{"text":75,"@type":76},"Assigning a classical role to one agent can lead to a monolithic teammate that is hard to build, test, maintain, and delegate. Conversely, defining very fine-grained micro-agents increases coordination overhead between agents and humans.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does pm4aa derive project-specific agent roles and specifications?",{"text":80,"@type":76},"pm4aa treats version control and issue management activity as event logs, uses object-centric process mining to capture multi-object task scopes and interactions, and applies declarative process mining to extract behavioral constraints that guide agent execution.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the approach evaluated in the reported proof of concept?",{"text":84,"@type":76},"The authors implemented pm4aa with the LangGraph framework and evaluated it on the open-source Commitizen project using a case study. Evaluation included functional testing of the generated agents and a user study with ten participants assessing alignment with human expectations.","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"]