[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-638984-105":59,"doc-detail-638984-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-motivational-architecture-for-conversational-agi","A Motivational Architecture for Conversational AGI","","Motivational architectures in cognitive AI have largely focused on physical agents that regulate bodily needs, yet conversational agents operate through linguistic sensorimotor loops and act via speech acts, tool invocations, strategic silences, and memory updates. This paper proposes a dialogue-native reinterpretation of the OpenPsi motivational lineage combined with MetaMo’s higher-level motivational scaffold for agents on a modular execution substrate. Homeostasis is reframed as regulation of competence, uncertainty reduction, affiliation, affinity, legitimacy, nurturing, and aesthetic coherence. The paper presents an aten-stage pipeline, a dual urgency-fast and deliberative multi-goal decision strategy, and a functional distinction between pre-action feelings and post-action emotions, then illustrates the framework on two example agents while outlining extensions toward social robotics and domain-generic human-level AGI.",{"@graph":69,"@context":122},[70,84,105],{"@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/a-motivational-architecture-for-conversational-agi/638984/",{"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/a-motivational-architecture-for-conversational-agi/638984.png","ImageObject",300,407,{"name":92,"@type":93},"Alexandar","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-22",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why does motivational architecture differ for conversational agents compared with physical agents?","Question",{"text":112,"@type":113},"Conversational agents rely on a linguistic sensorimotor loop and an environment defined by a user’s evolving mental and social state. Their actions are speech acts, tool invocations, silences, reframings, and memory updates rather than motor commands.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the paper reinterpret homeostasis for dialogue-native agents?",{"text":117,"@type":113},"Homeostasis is reframed from regulating bodily deficits to regulating competence, uncertainty reduction, affiliation, affinity, legitimacy, nurturing, and aesthetic coherence within dialogue.",{"name":119,"@type":110,"acceptedAnswer":120},"What are the three main contributions proposed in the paper?",{"text":121,"@type":113},"The paper proposes: (1) a ten-stage motivational processing pipeline separating cognitive modulation from situational appraisal, (2) a dual decision strategy combining urgency-driven fast response with deliberative multi-goal optimization, and (3) an architecturally useful distinction between pre-action feelings and post-action emotions.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},638984,1792700983,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":36},962090768658,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","arXiv :2606 .054 1 1v 1 [ cs .AI] 3 Jun 2026  \nA Motivational Architecture for Conversational  \nAGI  \nAnna Mikeda 1 and Ben Goertzel2  \n1 Glass Umbrella  \n[amikeda17@gmail.com](amikeda17@gmail.com)  \n2 SingularityNet  \n[ben@singularitynet.io](ben@singularitynet.io)  \nAbstract. Motivational architectures in cognitive AI have largely been designed for physical agents regulating bodily needs. Conversational agents operate in a different regime: their sensorimotor loop is linguistic, their environment is a user’s evolving mental state, and their consequential actions are speech acts, tool invocations, and strategic silences. This paper proposes a conversational reinterpretation of the OpenPsi motivational lineage, coupled to MetaMo’s higher-level motivational scaffold, for agents built on a modular execution substrate. Homeostasis is recast in dialogue-native terms: the agent regulates competence, uncertainty reduction, affiliation, affinity, legitimacy, nurturing, and aesthetic coherence rather than bodily deficits. We propose three contributions: aten-stage motivational processing pipeline that architecturally separates cognitive modulation from situational appraisal; a dual decision strategy blending urgency-driven fast response with deliberative multi-goal optimization; and an architecturally useful distinction between pre-action feelings and post-action emotions as functionally different forms of affect.  \nWe specialize the framework to two example agents—CompanionAgent and ResearchAgent — and sketch its extension to social robotics and domain-generic human-level AGI.  \nKeywords: AGI · motivational architecture · conversational agents · OpenPsi · MetaMo · neurosymbolic AI · feelings and emotions  \n1 Introduction  \nMotivation is one of the hardest problems in AGI system design. It is more of a cognitive, emotional, architectural and dynamical issue, rather than the sort of algorithmic issue that computer science tends to address, but this does not make it conceptually or pragmatically any simpler.  \nReinforcement learning gestures toward the problem of motivation but does not solve it. A robust AGI system must balance multiple drives, maintain selfcoherence across time, and respond adaptively to shifting contexts without destabilizing into pathological self-modification or opportunistic misalignment.  \nThe MetaMo framework [5] addresses these issues at the formal level by treating motivation as a joint state of goals and modulators, with a mathematically  \n2 A. Mikeda and B. Goertzel  \nspecified appraisal process and decision process composed into a stable overall update dynamic. OpenPsi-style motivational dynamics provide the concrete lineage for the appraisal and modulation layer we develop here [3], while MetaMo and its operationalization in OpenPsi-related equations [5] provide the broader formal scaffold. Both traditions are themselves inspired by Bach’s MicroPsi [1], which updates modulators like arousal, resolution, and selection threshold in response to stimulus features.  \nThese frameworks, however, have been developed mainly with a mix of general AGI architecture and embodied inference control in mind. And while traditional forms of embodiment (e.g. robotic and virtual) remain critical for AGI, the AI field also currently involves a lot of momentum behind conversational agents, which introduce a different design regime. Their primary sensorimotor loop is linguistic; their most important environment is usually a user’s evolving mental and social state; and their most consequential actions are speech acts, tool invocations, silences, reframings, and memory updates rather than motor commands.  \nMost current conversational agents rely on large language models with no explicit motivational architecture; if motivation appears at all, it is implicit in prompts or fine-tuning. Recent systems such as Generative Agents [7], DesireDriven Autonomy [10], and Inner Thoughts [6] move toward internal structure, but still do not prov","cbCaiqYHjm0xPpXh","https://ap.wps.com/l/cbCaiqYHjm0xPpXh","pdf",374390,16,"English","# Introduction\n## Motivation and existing frameworks\n## Conversational-agent reinterpretation\n# Contributions","[{\"question\":\"Why does motivational architecture differ for conversational agents compared with physical agents?\",\"answer\":\"Conversational agents rely on a linguistic sensorimotor loop and an environment defined by a user’s evolving mental and social state. Their actions are speech acts, tool invocations, silences, reframings, and memory updates rather than motor commands.\"},{\"question\":\"How does the paper reinterpret homeostasis for dialogue-native agents?\",\"answer\":\"Homeostasis is reframed from regulating bodily deficits to regulating competence, uncertainty reduction, affiliation, affinity, legitimacy, nurturing, and aesthetic coherence within dialogue.\"},{\"question\":\"What are the three main contributions proposed in the paper?\",\"answer\":\"The paper proposes: (1) a ten-stage motivational processing pipeline separating cognitive modulation from situational appraisal, (2) a dual decision strategy combining urgency-driven fast response with deliberative multi-goal optimization, and (3) an architecturally useful distinction between pre-action feelings and post-action emotions.\"}]","A Motivational Architecture for Conversational AGI | PDF"]