[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-638732-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-638732-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","the-agency-gap-using-a-minimal-coordination-game-human-human-and-human-ai-collaboration","The Agency Gap - Using a Minimal Coordination Game - Human-Human and Human-AI Collaboration","","The Agency Gap investigates how cooperative agents coordinate toward a shared goal when partners may pursue competing objectives, and whether human-like shared agency emerges in human–AI collaboration. Adults and children play a minimal non-verbal coordination game with agentic AI partners instantiated as individual RL, joint RL, LLM-based agents, and LLMs prompted with theory-of-mind cues. Results show humans achieve the highest success, efficiency, and commitment; AI partners elicit signaling under minimal sociality, yet performance costs and reduced coordination efficiency appear, especially for children.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/the-agency-gap-using-a-minimal-coordination-game-human-human-and-human-ai-collaboration/638732/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/the-agency-gap-using-a-minimal-coordination-game-human-human-and-human-ai-collaboration/638732.png","ImageObject",300,407,{"name":42,"@type":43},"Rhys","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-10-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",5,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the core problem addressed by The Agency Gap?","Question",{"text":63,"@type":64},"The work targets how agents coordinate actions toward a joint goal under potentially competing goals, focusing on whether shared agency can be established through commitment and signaling.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was shared agency tested in the collaboration studies?",{"text":68,"@type":64},"Participants played a minimal non-verbal coordination game with AI partners that differed in sociality, including individual RL, joint RL, LLMs, and LLMs with theory-of-mind prompts.",{"name":70,"@type":61,"acceptedAnswer":71},"What did the studies find about human-AI collaboration compared with human-human collaboration?",{"text":72,"@type":64},"Human-human coordination produced uniquely high joint commitment and coordination efficiency, while human-AI coordination reduced these metrics; nonetheless, minimally social AI agents could elicit human signaling.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},638732,1792697758,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,100,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":55,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":22,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":80,"read_time":30},687207024643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","The Agency Gap: Testing Human-Human and Human-AI Collaboration  \nUsing a Minimal Coordination Game  \nShaozhe Cheng 1,2 , Tao Gao2 , Michael Tomasello 1 & Tamar Kushnir 1  \n1Department of Psychology & Neuroscience, Duke University 2Department of Communication, UCLA  \nVisual Intelligence Lab  \n\n|  | Motivation |  |  |  |\n| --- | --- | --- | --- | --- |\n|  |  |  |  |  |\n| The Agency Gap\u003Cbr>\u003Cbr>• A central challenge of cooperation is how agents coordinate their actions toward a joint goal amid potentially competing goals.\u003Cbr>• Humans evolved shared agency to solve this coordination problem (Searle, 1990; Tomasello, 2022): they form shared intentions, commit to them, and use signaling to make their goals transparent to partners.\u003Cbr>• Modern AI achieves impressive outcomes, yet its“agency” is often treated as a byproduct of optimizing predefined objectives (RL and LLMs) . As a result, it functions more like a tool (asocial or social) than as a genuinely collaborative agent.\u003Cbr>\u003Cbr>Central Questions\u003Cbr>1. To what extent is human-AI collaboration human-like and human-compatible?\u003Cbr>2. Do the signatures of shared agency (joint commitment and social signaling) emerge when the partner is an AI? Does this depend on the sociality of the AI partner?\u003Cbr>3. Can children, who default to shared agency, adapt to AI partners that lack it? |  |  |  |  |\n| |  | Game Demo & Preprint paper\u003Cbr>[shaozhe.cheng@duke.edu](shaozhe.cheng@duke.edu) | |  |\n\n\n|  | Design |  |  |  |  | Study 1: Adults (N = 150) |  |  |  |  |  |  | Ongoing work |  |  |  |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| A non-verbal coordination game\u003Cbr>\u003Cbr>• Two players each move one step simultaneously.\u003Cbr>• A round succeeds if both reach the same goal.\u003Cbr>• A new alternative goal could appear during navigation.\u003Cbr>\u003Cbr>Agentic AI partners\u003Cbr>(Every partner is described neutrally as “another player”)\u003Cbr>\u003Cbr>1. Individual RL\u003Cbr>2. Joint RL\u003Cbr>3. LLM ( GPT 4.1 mini)\u003Cbr>4. LLM + ToM\u003Cbr>maximizes individual utility (asocial) maximizes joint utility (social tool)\u003Cbr>choose the best next step with map image + symbolic state info first infers the partner's goal, then acts\u003Cbr>Measures\u003Cbr>\u003Cbr>• Objective performance: Success & Efficiency\u003Cbr>• Signatures of shared agency: Commitment & Signaling\u003Cbr>|  |  |  | \u003Cbr>100806040200\u003Cbr>100806040200\u003Cbr>Human  Indiv. RL\u003Cbr>Success Rate (%)\u003Cbr>100.0 98.9 98.9 90.8\u003Cbr>83.6\u003Cbr> Joint RL  LLM  LLM-ToM\u003Cbr>Coordination Efficiency (%)• Human-human showed the 100 97.1 91.7 92.0 84.0 highest success, efficiency, and\u003Cbr>80 80.2 commitment. 60\u003Cbr>• Adults adapt their strategies to\u003Cbr>40\u003Cbr>different AI agents for\u003Cbr>20\u003Cbr>successful outcomes.\u003Cbr>0\u003Cbr>Commitment (%) Signaling Move (%)\u003Cbr>100806040200\u003Cbr>* *\u003Cbr>56.7\u003Cbr>55.6  \u003Cbr>46.0 42.8\u003Cbr>27.2\u003Cbr>\u003Cbr>• Commitment predict efficiency (p \u003C .001) .\u003Cbr>• LLM agents are suboptimal in visual-spatial, non-verbal games; ToM prompts helped.\u003Cbr>• Minimal sociality (Joint RL, LLM-ToM) can elicit human signaling, even with suboptimal performance.\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>|  |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  | From outcome optimization to reverse engineering (social) agency:\u003Cbr>A shared-agency model\u003Cbr>\u003Cbr>Human collaborate with this model?\u003Cbr>Pilot findings: Adults are more committed, more efficient, and more likely to signal. |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  | Study 2: Children, 5–7 yrs (N = 109, ongoing) |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  | 100806040200\u003Cbr>100806040200\u003Cbr>Success Rate (%)\u003Cbr>Coordination Efficiency (%)\u003Cbr>100\u003Cbr>80 • 5-to 7-year-old children\u003Cbr>60 successfully adapt their\u003Cbr>40 strategies to different AI. 20\u003Cbr>• Commitment and signaling\u003Cbr>Commitment (%)\u003Cbr>\u003Cbr>100806040200\u003Cbr>Signaling Move (%)\u003Cbr>**\u003Cbr>45.0 31.0\u003Cbr>emerge with joint-RL (social tool) .\u003C","cbCaiuDg7LFajxCK","https://ap.wps.com/l/cbCaiuDg7LFajxCK","pdf",956553,"English","# Motivation and Central Questions\n# Game Design and Agentic AI Partners\n## Study 1: Adults\n## Study 2: Children (Ongoing)\n# Conclusions","[{\"question\":\"What is the core problem addressed by The Agency Gap?\",\"answer\":\"The work targets how agents coordinate actions toward a joint goal under potentially competing goals, focusing on whether shared agency can be established through commitment and signaling.\"},{\"question\":\"How was shared agency tested in the collaboration studies?\",\"answer\":\"Participants played a minimal non-verbal coordination game with AI partners that differed in sociality, including individual RL, joint RL, LLMs, and LLMs with theory-of-mind prompts.\"},{\"question\":\"What did the studies find about human-AI collaboration compared with human-human collaboration?\",\"answer\":\"Human-human coordination produced uniquely high joint commitment and coordination efficiency, while human-AI coordination reduced these metrics; nonetheless, minimally social AI agents could elicit human signaling.\"}]","The Agency Gap - Using a Minimal Coordination Game - Human-Human and Human-AI Collaboration | PDF"]