[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85536-en":3,"doc-seo-85536-105":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},85536,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Grounding Machine Creativity in Game Design Knowledge Representations","Creatively translating complex gameplay ideas into executable artifacts remains a core challenge in computational game creativity. Gameplay design patterns offer structured representations that let designers decompose high-level goals into entities, constraints, and rule-driven dynamics. Goal playable concepts operationalize goal patterns as Unity-based playable implementations, enabling compositional design. This work frames scalable pattern realization as constrained executable creative synthesis under Unity structural requirements, and empirically tests whether LLMs can generate goal-pattern-conditioned Unity code.","Grounding Machine Creativity in Game Design Knowledge Representations: Empirical Probing of LLM-Based Executable Synthesis of Goal Playable Patterns  \nunder Structural Constraints  \nHugh Xuechen Liu, Kıvanc¸ Tatar  \nChalmers University of Technology and University of Gothenburg  \n[xuechen@chalmers.se](xuechen@chalmers.se) , [tatar@chalmers.se](tatar@chalmers.se)  \narXiv :2603 .07101v4 [ cs .AI] 30 Apr 2026  \nAbstract  \nCreatively translating complex gameplay ideas into executable artifacts (e.g., games as Unity projects and code) remains a central challenge in computational game creativity. Gameplay design patterns provide a structured representation for describing gameplay phenomena, enabling designers to decompose high-level ideas into entities, constraints, and rule-driven dynamics. Among them, goal patterns formalize common player–objective relationships. Goal Playable Concepts (GPCs) operationalize these abstractions as playable Unity engine implementations, supporting experiential exploration and compositional gameplay design.  \nWe frame scalable playable pattern realization as a problem of constrained executable creative synthesis: generated artifacts must satisfy Unity’s syntactic and architectural requirements while preserving the semantic gameplay meanings encoded in goal patterns. This dual constraint limits scalability. Therefore, we investigate whether contemporary large language models (LLMs) can perform such synthesis under engine-level structural constraints and generate Unity code (as games) structured and conditioned by goal playable patterns  \nUsing 26 goal pattern instantiations, we compare a direct generation baseline (natural language → C\\# → Unity) with pipelines conditioned on a human-authored Unity-specific intermediate representation (IR), across three IR configurations and two open-source models (DeepSeek-Coder-V2-Lite-Instruct and Qwen2.5-Coder-7B-Instruct) . Compilation success is evaluated via automated Unity replay. We propose grounding and hygiene failure modes, identifying structural and project-level grounding as primary bottlenecks.  \nIntroduction  \nComputational Creativity (CC) investigates how computational systems generate novel, coherent, and valuable artifacts (Boden 2004; Colton, Charnley, and Pease 2011) . In computational game creativity—CC “within and for” digital games (Liapis, Yannakakis, and Togelius 2014)—an additional constraint is unavoidable: artifacts must be executable and playable. We frame this challenge as creative realization (Costikyan 2002): given structured game design knowledge, can a computational system reliably instantiate it as operational and playable content? Executable viability is not merely an engineering gate but a necessary condition for artifact existence under real engine constraints. A second motivation is scale: human-authored  \nplayable concept implementations (Kultima et al. 2020; Lyu, Holopainen, and Bjrk 2023) are rich but do not scale; LLM-driven pipelines that reliably instantiate design knowledge as executable artifacts open pathways to large-scale exploration of gameplay design spaces.  \nWe adopt a representation-first perspective (Shaker, Togelius, and Nelson 2016; Togelius et al. 2011; Liapis, Smith, and Shaker 2016): rather than treating LLM generation as direct text-to-code synthesis, we ask whether explicit design knowledge encoded as a structured intermediate representation (IR) can scaffold reliable creative realization. Gameplay design patterns (Bjork and Holopainen 2005) provide a structured representation for recurring interaction structures; among these, goal patterns describe how player objectives are constituted through entities, constraints, and rulegoverned interactions. Instantiating a goal pattern in Unity requires coherent object configuration, correct component attachment, and runtime wiring—making goal-pattern realization a stringent testbed for creative realization under real engine constraints.  \nUsing 26 goal pattern refe","cbCaipgb2niRVkij","https://ap.wps.com/l/cbCaipgb2niRVkij","pdf",314829,3,1,19,"English","en",105,"# Abstract\n# Introduction\n## Representation-first perspective\n## Evaluation setup and baseline vs. IR-conditioned pipelines\n# Contributions\n# Note on model scope","[{\"question\":\"什么是 goal playable concepts（GPCs）以及它们如何落地到 Unity？\",\"answer\":\"GPCs 将 goal patterns 的抽象关系操作化为可在 Unity 引擎中运行的可玩实现，从而支持可体验探索与组合式玩法设计。其关键是用结构化的目标-实体-约束关系指导可执行代码与项目结构。\"},{\"question\":\"论文如何定义“受结构约束的可执行创造合成”问题？\",\"answer\":\"生成产物必须同时满足 Unity 的语法与架构要求，并保留 goal patterns 中编码的玩法语义。双重约束会限制可扩展性，因此作者将其作为约束下的可执行创造合成来研究。\"},{\"question\":\"实验如何评估 LLM 生成的 Unity 代码是否成功？\",\"answer\":\"作者使用 26 个 goal pattern 的实例，比对自然语言到 C# 到 Unity 的直接生成基线与多种 IR 条件管线。通过自动 Unity replay 验证编译成功，并对失败进行结构化分析，提出 grounding 与 hygiene 失败模式与主要瓶颈。\"}]",1784204275,48,{"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},"grounding-machine-creativity-in-game-design-knowledge-representations","",{"@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/grounding-machine-creativity-in-game-design-knowledge-representations/85536/",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","2026-07-24","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},"什么是 goal playable concepts（GPCs）以及它们如何落地到 Unity？","Question",{"text":75,"@type":76},"GPCs 将 goal patterns 的抽象关系操作化为可在 Unity 引擎中运行的可玩实现，从而支持可体验探索与组合式玩法设计。其关键是用结构化的目标-实体-约束关系指导可执行代码与项目结构。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"论文如何定义“受结构约束的可执行创造合成”问题？",{"text":80,"@type":76},"生成产物必须同时满足 Unity 的语法与架构要求，并保留 goal patterns 中编码的玩法语义。双重约束会限制可扩展性，因此作者将其作为约束下的可执行创造合成来研究。",{"name":82,"@type":73,"acceptedAnswer":83},"实验如何评估 LLM 生成的 Unity 代码是否成功？",{"text":84,"@type":76},"作者使用 26 个 goal pattern 的实例，比对自然语言到 C# 到 Unity 的直接生成基线与多种 IR 条件管线。通过自动 Unity replay 验证编译成功，并对失败进行结构化分析，提出 grounding 与 hygiene 失败模式与主要瓶颈。","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]