[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83844-en":3,"doc-seo-83844-105":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},83844,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","AI Agent Pull Requests on GitHub Frequency Structure and Merge Conflict Rates","AI coding agents can concurrently submit Pull Requests (PRs) to the same GitHub repository, yet prior work lacks evidence on how often such concurrent submissions occur. Using the AIDev-pop dataset (33,596 PRs across 2,807 repositories), the study quantifies co-active, agent-authored PR pairs and shows large shares of total agent-generated PRs under both exact temporal overlap and a one-week collaboration window. It also replays three-way git merges and measures textual conflict rates, linking conflicts to file types and structural changes.","AI Agent Pull Requests on GitHub: Frequency, Structure, and  \nMerge Conflict Rates  \nGeorge Xu∗ Harvard Medical School / Massachusetts General Hospital Boston, Massachusetts, USA  \nArjun Subramanian∗ Massachusetts Institute of Technology Computer Science & Artificial Intelligence Lab Cambridge, Massachusetts, USA  \nNithilan Karthik∗ DevRev AI LLC San Francisco, California, USA  \narXiv :2607 .04697v2 [ cs . SE] 7 Jul 2026  \nAbstract  \nAI coding agents may generate and submit Pull Requests (PRs) to the same repository at the same time. However, research concerning the extent of concurrent submission by AI coding agents to a common repository does not exist. This paper uses the AIDev-pop dataset (33,596 PRs in 2,807 repositories) to provide the first empirical examination of the prevalence of concurrent submission using PRs authored by agents. We report that when considering exact temporal overlap, 40.2% of repositories contain co-active agent-authored PR pairs; further, the co-active pairs account for 79.4% of all PRs generated by an AI agent. When we examine co-activity within a one week collaboration window, the percentages are increased to 53.4% and 95.0%, respectively. For the majority of the co-active PR pairs (underlying the vast majority of which are intra-agent authored), both PRs were authored by the same agent, while only 0.5% of coactive pairs were cross-agent, and occurred in only 122 out of 2807 total repositories examined (or approximately 4.3%). Additionally, we replayed actual three way git merges on 747 unique co-active pairs (one per repository), and computed the percentage of textual conflict encountered during the merge operation to combine the two PRs in each pair. We observed that the percentage of textual conflict encountered was significantly higher for cross-agent pairs compared to intra-agent pairs: 41.7% vs. 19.8%, respectively, with non-overlapping 95% confidence intervals. Lastly, we developed a classification system based on the detection of conflict reported by git, and determined that the majority of conflicts resulted from modifications to source code files (84.4% of conflicted files) and not dependency manifest files; further, nearly 42% of conflicts we observed were structural (i.e., modify/delete or add/add) . Since these metrics are limited to the textual level of granularity, they represent conservative lower bounds on costs incurred due to the uncoordinated contributions of multiple AI teammates contributing to a single project.  \nKeywords  \nAI coding agents, pull requests, merge conflicts, concurrency, mining software repositories, AIDev, automated engineering  \n1 Introduction  \nEngineering automation has undergone considerable progress since the first generation of linear, user-interaction-based auto-completion utilities. Today’s engineering agents operate independently and in real-time; they have complete environmental understanding and  \n∗ All authors contributed equally to this work.  \ntherefore can independently assess issues, write fixes for applications, conduct internal testing cycles, and submit pull requests (PRs) to the operational master branch [1] autonomously. Over the past few years, datasets such as the AIDev ecosystem data set [2], which includes an empirical collection of more than 932,000 pull requests submitted across 116,211 multi-scaled GitHub repositories, have demonstrated that automated developers are creating source code in unprecedented numbers, which indicates a shift toward hybrid or completely autonomous collaborative programming.  \nA structural issue of coordination between architecture and text arises due to the increased use of autonomous development of source code. In addition to having numerous agent instances—or various agent types—deployed to a single target project at the sametime, the typical outcome is a large degree of overlap during each instance’s work. Even though standard branching models for gitbased systems support two separate PRs targeting t","cbCaibkp3m8gJiNr","https://ap.wps.com/l/cbCaibkp3m8gJiNr","pdf",709707,1,7,"English","en",105,"# Abstract\n# 1 Introduction","[{\"question\":\"What dataset and scope does the study use to analyze concurrent agent PRs on GitHub?\",\"answer\":\"The study uses the AIDev-pop dataset containing 33,596 pull requests across 2,807 repositories authored by automated developers (agents).\"},{\"question\":\"How common are concurrent agent-authored PRs under exact temporal overlap and within a one-week window?\",\"answer\":\"Under exact temporal overlap, 40.2% of repositories contain co-active agent-authored PR pairs, and those pairs account for 79.4% of all agent-generated PRs. Within a one-week collaboration window, the figures increase to 53.4% and 95.0%, respectively.\"},{\"question\":\"Are merge conflicts more frequent for cross-agent PR pairs than for intra-agent PR pairs, and what drives those conflicts?\",\"answer\":\"Textual conflicts are significantly higher for cross-agent pairs (41.7%) than intra-agent pairs (19.8%). The classification results indicate most conflicts stem from source code file modifications (84.4%) rather than dependency manifest files, and nearly 42% of conflicts are structural (e.g., modify/delete or add/add).\"}]",1784190935,18,{"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},"ai-agent-pull-requests-on-github-frequency-structure-and-merge-conflict-rates","",{"@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/ai-agent-pull-requests-on-github-frequency-structure-and-merge-conflict-rates/83844/",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 dataset and scope does the study use to analyze concurrent agent PRs on GitHub?","Question",{"text":75,"@type":76},"The study uses the AIDev-pop dataset containing 33,596 pull requests across 2,807 repositories authored by automated developers (agents).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How common are concurrent agent-authored PRs under exact temporal overlap and within a one-week window?",{"text":80,"@type":76},"Under exact temporal overlap, 40.2% of repositories contain co-active agent-authored PR pairs, and those pairs account for 79.4% of all agent-generated PRs. Within a one-week collaboration window, the figures increase to 53.4% and 95.0%, respectively.",{"name":82,"@type":73,"acceptedAnswer":83},"Are merge conflicts more frequent for cross-agent PR pairs than for intra-agent PR pairs, and what drives those conflicts?",{"text":84,"@type":76},"Textual conflicts are significantly higher for cross-agent pairs (41.7%) than intra-agent pairs (19.8%). The classification results indicate most conflicts stem from source code file modifications (84.4%) rather than dependency manifest files, and nearly 42% of conflicts are structural (e.g., modify/delete or add/add).","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"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"]