[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83714-en":3,"doc-seo-83714-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},83714,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Second MOASEI Competition at AAMAS 2026 Technical Report","Second Methods for Open Agent Systems Evaluation Initiative (MOASEI) Competition at AAMAS 2026 presents a benchmark for evaluating multi-agent decision-making under open-system conditions. Building on MOASEI 2025, the 2026 version preserves wildfire fighting, cybersecurity, and ride-sharing domains, and adds a bonus wildfire track with frame openness. Reporting metrics emphasize task completions and time, plus mean value of completed tasks. Participation was limited, with results focused on ride-sharing and a DLC-based planner winning against baseline policies.","Second MOASEI Competition at AAMAS’2026: A Technical Report  \nCeferino Patino  \nUniversity of Nebraska-Lincoln Lincoln, Nebraska, United States [cpatino2@unl.edu](cpatino2@unl.edu)  \nTyler J. Billings  \nUniversity of Nebraska-Lincoln Lincoln, Nebraska, United States [tbillings4@unl.edu](tbillings4@unl.edu)  \nAlireza Saleh Abadi  \nUniversity of Nebraska-Lincoln Lincoln, Nebraska, United States [asalehabadi2@unl.edu](asalehabadi2@unl.edu)  \nDaniel Redder  \nUniversity of Georgia-Athens Athens, Georgia, United States [daniel.redder@uga.edu](daniel.redder@uga.edu)  \nAdam Eck  \nOberlin College Oberlin, Ohio, United States [aeck@oberlin.edu](aeck@oberlin.edu)  \nPrashant Doshi  \nUniversity of Georgia-Athens Athens, Georgia, United States [pdoshi@uga.edu](pdoshi@uga.edu)  \narXiv :2607 .03399v 1 [ cs .MA] 3 Jul 2026  \nLeen-Kiat Soh  \nUniversity of Nebraska-Lincoln Lincoln, Nebraska, United States [lksoh@unl.edu](lksoh@unl.edu)  \nABSTRACT  \nWe describe the 2026 Methods for Open Agent Systems Evaluation Initiative (MOASEI) Competition, a benchmark event for evaluating multi-agent decision-making under open-system conditions. Building on the inaugural 2025 competition, the 2026 edition retained wildfire fighting, cybersecurity, and ride-sharing domains while adding a bonus wildfire track with frame openness, in which agent equipment states such as suppressant capacities and firefighting range vary over time. The competition also expanded its reporting metrics to emphasize total task completions, mean task-completion time, and mean value of completed tasks. Participation in 2026 was limited: eight teams registered, but only one team submitted a final entry, and that entry targeted the ride-sharing track. The submitted DLC approach used planning and replanning to solve routing problems across agents as passengers appeared. This report summarizes the 2026 competition design, highlights differences from the previous year, and reports ride-sharing evaluation results against baseline policies. DLC is recognized as the 2026 ride-sharing track winner among submitted teams.  \nKEYWORDS  \nopen agent systems, multiagent systems, artificial intelligence, MOASEI competition  \nACM Reference Format:  \nCeferino Patino, Tyler J. Billings, Alireza Saleh Abadi, Daniel Redder, Adam Eck, Prashant Doshi, and Leen-Kiat Soh. 2026. Second MOASEI Competition at AAMAS’2026: A Technical Report. 5 pages.  \n1 INTRODUCTION  \nThe second annual Methods for Open Agent Systems Evaluation Initiative (MOASEI) Competition was held on May 25, 2026 in Paphos, Cyprus as part of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS’2026) . The MOASEI competition series evaluates multi-agent AI systems in  \nThis work is licensed under a Creative Commons Attribution International 4 .0 License.  \n, 2026. © 2026 Copyright held by the owner/author(s) .  \nopen agent environments where agents, tasks, and the capabilities of agents may change over time. The competition is built on the freerange-zoo environment suite [2], which implements benchmark domains inspired by open agent systems [1] . The inaugural competition in 2025 [3] established the core evaluation infrastructure and introduced three benchmark tracks: wildfire fighting, cybersecurity, and ride-sharing.  \nThe 2026 competition was designed to build upon the initial success of MOASEI’2025 . Rather than introducing an entirely new benchmark suite, the goals were to refine the evaluation tracks, add a new form of openness, improve the interpretability of results through more task-centered metrics, and continue to grow the community of researchers addressing the real-world complexities imposed by open agent systems. Participation was lower than in the inaugural year: eight teams registered, one team submitted a final solution, and only the ride-sharing track received a submission. This report focuses on documenting the 2026 updates and providing a concise analysis of the winning ride-sharing submission ","cbCaie59KQdcVMOk","https://ap.wps.com/l/cbCaie59KQdcVMOk","pdf",647101,1,5,"English","en",105,"# Introduction\n## Background\n## Summary of the 2025 MOASEI Competition","[{\"question\":\"What does the MOASEI competition evaluate in 2026?\",\"answer\":\"It evaluates multi-agent AI decision-making in open environments where agents, tasks, and agent capabilities can change over time.\"},{\"question\":\"Which benchmark tracks are included in the 2026 edition?\",\"answer\":\"The 2026 competition includes wildfire fighting, cybersecurity, and ride-sharing, and adds a bonus wildfire track that explicitly introduces frame openness.\"},{\"question\":\"How is performance reported for the 2026 competition?\",\"answer\":\"Metrics emphasize total task completions, mean task-completion time, and the mean value of completed tasks, used to compare submissions against baseline policies.\"}]",1784189933,13,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"second-moasei-competition-at-aamas-2026-technical-report","",{"@graph":35,"@context":84},[36,53,67],{"@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/second-moasei-competition-at-aamas-2026-technical-report/83714/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What does the MOASEI competition evaluate in 2026?","Question",{"text":74,"@type":75},"It evaluates multi-agent AI decision-making in open environments where agents, tasks, and agent capabilities can change over time.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which benchmark tracks are included in the 2026 edition?",{"text":79,"@type":75},"The 2026 competition includes wildfire fighting, cybersecurity, and ride-sharing, and adds a bonus wildfire track that explicitly introduces frame openness.",{"name":81,"@type":72,"acceptedAnswer":82},"How is performance reported for the 2026 competition?",{"text":83,"@type":75},"Metrics emphasize total task completions, mean task-completion time, and the mean value of completed tasks, used to compare submissions against baseline policies.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":21,"slug":136},19,"General","general"]