[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83698-en":3,"doc-seo-83698-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83698,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making","Large Language Models (LLMs) are used to improve decision-making across everyday and safety-critical settings, seeking both alignment with human expectations and protection from AI non-determinism. Human collaboration remains difficult because users often over- or under-rely on AI suggestions, and current systems are poorly calibrated to individual preferences. This work proposes a human-AI collaborative decision-making framework based on stochastic game modeling and the Human-Centric Reflective Architecture (HCRA), using human-calibrated models plus reinforcement learning agents with iterative linguistic feedback. Experiments show improved decision effectiveness and high-quality recommendations.","Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making  \nAndreas Kouridakis  \n[andreaskouridakis@outlook.com](andreaskouridakis@outlook.com)[ ](andreaskouridakis@outlook.com)University of Piraeus Piraeus, Greece  \nDimitrios Patiniotis Spyropoulos  \n[dimpatspy@gmail.com](dimpatspy@gmail.com)[ ](dimpatspy@gmail.com)University of Piraeus Piraeus, Greece  \nGeorge A. Vouros  \n[georgev@unipi.gr](georgev@unipi.gr)[ ](georgev@unipi.gr)University of Piraeus Piraeus, Greece  \narXiv :2607 .03025v 1 [ cs .AI] 3 Jul 2026  \nAbstract  \nThe use of Large Language Models (LLMs) across diverse areas of human activity—ranging from everyday tasks to safety-critical applications—aims to enhance decision-making effectiveness with minimal human feedback. Concurrently, it seeks to align decisions with human expectations, preferences, and needs while mitigating risks associated with AI non-determinism. However, humans frequently over-or under-rely on AI recommendations, and current AI systems remain poorly calibrated to human expectations. To address these challenges, we introduce a human-AI collaborative decision-making framework designed to augment human capabilities and align AI agents with human preferences and expectations. Specifically, this paper (a) formulates the collaborative decision-making task as a stochastic game between an AI agent anda human player, and (b) proposes the Human-Centric Reflective Architecture (HCRA), which integrates human-calibrated models with reinforcement learning agents that leverage linguistic feedback inan iterative, reflective process. Evaluation results demonstrate that HCRA significantly enhances decision-making effectiveness and delivers high-quality recommendations.  \nCCS Concepts  \n• Computing methodologies → Stochastic games; Learning from critiques; Reinforcement learning; • Information systems → Decision support systems.  \nKeywords  \nAgentic AI, Human-centric AI, Collaborative Decision Making, Large Language Models, Language Agents, Reinforcement Learning, Alignment  \n1 Introduction  \nIn many collaborative decision-making environments, humans and AI agents engage in an interactive feedback loop. This iterative process aims to: (a) guide agents toward human-acceptable recommendations,(b) enable users to express and refine their preferences and expectations, and (c) allow agents to learn from historical interactions. Such tight interaction is vital in high-stakes domains (e.g., [4], [9]) where humans must retain ultimate decision-making authority.  \nHowever, effective human-AI collaboration remains a challenge. When partnering with AI, human performance often falls short of expectations [14] . While AI explanations can influence user decisions [13], they frequently fail to improve system understanding or properly calibrate trust [14] [7] [3] [27] [24] [21] . This shortfall  \nis especially critical when users must dedicate limited cognitive bandwidth to time-sensitive, high-consequence problems [17] . Furthermore, high recommendation accuracy alone is insufficient to build trust; effective collaboration requires AI systems to optimize for human utility alongside core task objectives [1],[23] ..  \nFocusing on LLM-assisted agents, our work is motivated by two core limitations. First, miscalibrated human expectations regarding AI capabilities often trigger over-or under-reliance [2] [26]  \n[6] . Second, rather than relying solely on large-scale training followed by aggregated alignment (e.g., RLHF [28] [16]), we leverage test-time scaling [19] [10] and contextual test-time tuning. This approach establishes a human-centric workflow where high-quality decisions are made in-context based on user utility, enabling agents to dynamically refine recommendation quality and mitigate issues stemming from LLM non-determinism.  \nTo address these issues, we propose a human-centric reflective architecture (HCRA) for collaborative decision-making that integrates reinforcement learning (RL) language ag","cbCaitYWtZGYAY1X","https://ap.wps.com/l/cbCaitYWtZGYAY1X","pdf",3227700,3,1,24,"English","en",105,"# Introduction\n## Core challenges in human-AI collaboration\n## Motivation: LLM-assisted agents and calibration\n## Proposed solution and contributions\n# Related work","[{\"question\":\"What problem does the paper address in human-AI collaborative decision-making?\",\"answer\":\"It addresses miscalibrated human expectations and the resulting over- or under-reliance on AI recommendations, which limits trust and harms effectiveness. It also targets weaknesses in aligning AI decisions with human preferences under AI non-determinism.\"},{\"question\":\"How does the proposed framework model the collaboration between a human and an AI agent?\",\"answer\":\"The paper formulates collaborative decision-making as a stochastic game between an AI agent and a human player. It defines a human-utility objective optimized for user expectations and preferences, supporting convergence and termination guarantees.\"},{\"question\":\"What is HCRA and how does it improve recommendations?\",\"answer\":\"HCRA is a human-centric reflective architecture that integrates human-calibrated models with reinforcement learning language agents. It uses an iterative reflective process with linguistic feedback and tuning in context based on user utility and historical interactions.\"}]",1784189806,60,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"human-centric-reflective-architecture-for-human-ai-collaborative-decision-making","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/human-centric-reflective-architecture-for-human-ai-collaborative-decision-making/83698/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","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 problem does the paper address in human-AI collaborative decision-making?","Question",{"text":75,"@type":76},"It addresses miscalibrated human expectations and the resulting over- or under-reliance on AI recommendations, which limits trust and harms effectiveness. It also targets weaknesses in aligning AI decisions with human preferences under AI non-determinism.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed framework model the collaboration between a human and an AI agent?",{"text":80,"@type":76},"The paper formulates collaborative decision-making as a stochastic game between an AI agent and a human player. It defines a human-utility objective optimized for user expectations and preferences, supporting convergence and termination guarantees.",{"name":82,"@type":73,"acceptedAnswer":83},"What is HCRA and how does it improve recommendations?",{"text":84,"@type":76},"HCRA is a human-centric reflective architecture that integrates human-calibrated models with reinforcement learning language agents. It uses an iterative reflective process with linguistic feedback and tuning in context based on user utility and historical interactions.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":29,"slug":108},5,"Comic","comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]