[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-296682-105":59,"doc-detail-296682-en":123},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":116,"head_meta":118,"extra_data":120,"updated_unix":122},105,"en","compound-ai-ecosystem-agents-and-tools-to-improve-training-and-learning","Compound AI Ecosystem: Agents and Tools to Improve Training and Learning","","Military training aims to raise warfighter readiness for mission effectiveness while reducing time spent on exercises. It requires tailoring instruction to individual learners by using their prior training, operational experience, and role. A compound AI approach combines interacting AI models and tools, leveraging LLMs, multimodal models, human digital twins, and multiagent simulation. The framework integrates real-world training, simulated training, and feedback for continuous improvement via competency evaluation and curriculum-relevant procedural generation.",{"@graph":69,"@context":115},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/compound-ai-ecosystem-agents-and-tools-to-improve-training-and-learning/296682/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/compound-ai-ecosystem-agents-and-tools-to-improve-training-and-learning/296682.png","ImageObject",300,407,{"name":92,"@type":93},"Fahsai","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-18",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109],{"name":110,"@type":111,"acceptedAnswer":112},"How does the system personalize training and improve it over time?","Question",{"text":113,"@type":114},"Learners interact with instructor LLM-driven agents while separate evaluators identify gaps and generate personalized content; ongoing evaluation and procedural content generation then refine instruction tactics.","Answer","https://schema.org",{"og:url":83,"og:type":117,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":119,"canonical":83},"index,follow",{"doc_id":121,"site_id":62},296682,1790270288,{"code":4,"msg":5,"data":124},{"doc_id":121,"user_id":125,"nickname":92,"user_avatar":126,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":127,"file_id":128,"file_url":129,"file_type":130,"file_size":131,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":132,"language":133,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":134,"faqs":135,"seo_title":136,"seo_description":67,"update_tm":137,"read_time":138,"preview_page_count":4},549768702563,"https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083","Compound AI Ecosystem: Agents and Tools to Improve Training and Learning  \nSvitlana Volkova, Summer Rebensky, Laura Cassani, Bob McCormack, Adam Fouse, Sylvain Bruni, Gabe Ganberg and Kara Orvis  \nAptima, Inc.  \nWoburn, MA  \n{svolkova, srebensky, lcassani, rmccormack, afouse, sbruni, ganberg, [korvis}@aptima.com](korvis}@aptima.com)  \nABSTRACT  \nMilitary training strives to maximize warfighter readiness for mission effectiveness while minimizing the time spent in training exercises. Optimizing training outcomes requires an ability to tailor training to individual learners, considering their previous training, their operational experience, and their role. Compound AI systems, with multiple interacting AI models and tools, offer a promising solution to this problem by combining the advances seen in leveraging large language models (LLMs), multimodal foundation models (MFMs), human digital twins, and multiagent simulation. This paper describes a future concept in which an AI-driven ecosystem of agents could enhance curriculum-based training. Specifically, we propose a compound AI system and describe a framework for future learning systems that integrates three core components: real-world human training, simulated training, and feedback mechanisms for continuously improving training outcomes. Human learners interact with specialized LLM-driven agents acting as instructors, and separate AI agents to evaluate trainees’ competencies, identify knowledge gaps, and generate personalized training content to address deficiencies. To guide real-world instruction, the system leverages simulation using human learner digital twins that model personalities, backgrounds, competencies, and cognitive states. AI agents interact with the digital twins, evaluating their skills and tailoring instructions, generating data torefine instructional tactics, techniques, and procedures for human learners. Ongoing training improvement stems from two additional capabilities: competency evaluation that employs agents to assess human and digital twin proficiencies, and procedural generation of curriculum-relevant content to assist learners struggling with knowledge components. Together, these mechanisms continually optimize instructions to maximize training effectiveness. This novel compound ecosystem of AI-driven agents, simulated human digital twins and their optimized interactions aims to enhance knowledge acquisition, evaluate conditional understanding, and improve the comprehension of unique military concepts. By learning from human-AI exchanges and simulated outcomes, compound AI systems offer a path towards revolutionizing military training.  \nABOUT THE AUTHORS  \nDr. Svitlana Volkova Chief of AI at Aptima, leads the company's efforts in developing trustworthy and humancentric AI systems that address complex real-world challenges for the Department of Defense and other government agencies. Her research advances natural language processing and machine learning techniques, with a focus on graph neural networks, causal inference, and multimodal models. Dr. Volkova's pioneering work in AI-powered analytics has made significant contributions to explaining complex social systems and behaviors. A recognized leader in humancentered AI design, evaluation, and trustworthy AI systems, Dr. Volkova has spearheaded projects funded by DARPA, IARPA, SOCOM, DOE ASCR, and NNSA, advancing AI capabilities to support critical national security missions. Her expertise is reflected in over 70 peer-reviewed publications spanning AI, machine learning, and social media analytics. Dr. Volkova serves on program committees and review boards for top-tier AI conferences, including AAAI, ACL, EMNLP, and NeurIPS. As an advocate for diversity in technology, she is an active member of Women in Machine Learning. Dr. Volkova earned her PhD in Computer Science from Johns Hopkins University, where she was affiliated with the Center for Language and Speech Processing and the Human Language Tech","cbCaikbN58CCXgnj","https://ap.wps.com/l/cbCaikbN58CCXgnj","pdf",358257,13,"English","# Abstract\n# About the Authors","[{\"question\":\"How does the system personalize training and improve it over time?\",\"answer\":\"Learners interact with instructor LLM-driven agents while separate evaluators identify gaps and generate personalized content; ongoing evaluation and procedural content generation then refine instruction tactics.\"}]","Compound AI Ecosystem: Agents and Tools to Improve Training and Learning | PDF",1789735493,33]