[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85343-en":3,"doc-seo-85343-105":29,"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85343,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","MAGIC Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models","Multi-scene navigation—completing an objective in one bounded space and then crossing a portal into the next—remains labor-intensive because portals must share consistent endpoints, each furnished interior must stay navigable, and connectivity must remain coherent across many project files. MAGIC is a prompt-to-project four-stage pipeline that plans a shared transition-aware intermediate representation, validates portal reachability via flood-fill, generates scenes with transition scripts, and evaluates transitions by running them in play, achieving 0.99 precision, 0.95 recall, and 0.96 F1 on 100 benchmark cases.","MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models  \nTsz Hei Fan* , Choi Wing Fung* , Yuxuan Wan†, Shuqing Li‡, and Michael R. Lyu  \nDepartment of Computer Science and Engineering, The Chinese University of Hong Kong {thfan, serenefcw, [yxwan](yxwan}@link.cuhk.edu.hk)[}](yxwan}@link.cuhk.edu.hk)[@link.cuhk.edu.hk](yxwan}@link.cuhk.edu.hk), {sqli21, [lyu](lyu}@cse.cuhk.edu.hk)[}](lyu}@cse.cuhk.edu.hk)[@cse.cuhk.edu.hk](lyu}@cse.cuhk.edu.hk)  \narXiv :2607 . 1 1594v 1 [ cs .AI] 13 Jul 2026  \nAbstract—Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consistent endpoints on both sides, each interior must remain navigable once it is furnished, and the resulting connectivity must be kept consistent across many files. Recent large language model (LLM) and multimodal LLM (MLLM) scene generators have made single-interior synthesis dramatically cheaper, yet they produce one scene at a time and cannot, by naive repetition, yield a connected multi-scene world. We identify three obstacles that single-scene methods leave unsolved: cross-scene consistency, in-scene navigability, and the evaluation of whether a transition actually works. We present MAGIC, a prompt-to-project system that addresses all three. MAGIC is a four-stage pipeline that turns a single naturallanguage prompt into a runnable multi-scene game project: it plans a shared transition-aware intermediate representation, specifies each scene while enforcing portal reachability with a flood-fill validator, generates the scenes together with their transition scripts, and combines them into one project. Because existing single-scene fidelity metrics never execute a transition, we further introduce a transition-focused evaluation agent that runs each transition in play. On a new benchmark of 100 multiscene cases, MAGIC produces an executable project for every case and reaches 0.99 precision, 0.95 recall, and 0.96 F1 on endto-end transition identification; stage by stage, it recovers more ground-truth portals and yields markedly more navigable layouts than an LLM baseline and Holodeck. Our code is available at [https://github.com/sereneee1201/MAGIC/](https://github.com/sereneee1201/MAGIC/).  \nIndex Terms—Multi-Scene Generation, Scene Transition, Game Development, Text-to-3D Scene, Large Language Model  \nI. INTRODUCTION  \nMulti-scene navigation is a defining feature of contemporary 3D games. Dungeon crawlers, escape rooms, and RPGs all task the player with clearing an objective in one bounded space, then crossing a portal—a door, stairwell, or cutscene—into the next [1] . For the designer, this involves two coupled problems: each scene must be a coherent, navigable interior, and every portal must have consistent endpoints on both sides matching position, destination, and transition effect. This process requires the designer to maintain a connection graph by hand and to keep paired portals, transition scripts, and doorway clearance consistent across files. Prior work on game development identifies this hand-authored connectivity as oneof the most labor-intensive parts of 3D game production [2] .  \n* Fan and Fung contributed equally to this work and are co-first authors. † Wan is the project lead. ‡ Li is the corresponding author. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.  \nRecent LLM- and MLLM-driven scene generators have made the first half of the problem (i.e., interior generation) dramatically cheaper, but the second half (i.e., scene transition and connectivity) remains challenging. Systems such as Holodeck [3] and Scenethesis [4] synthesize a single furnished interior from a natural-language prompt, and surveys document a fast-growing text-to-3D landscape","cbCaiurMdRHB0C2W","https://ap.wps.com/l/cbCaiurMdRHB0C2W","pdf",2057715,1,11,"English","en",105,"# Abstract\n# Introduction\n## Multi-scene navigation problem\n## Limitations of prior single-scene generators\n## Three key obstacles (consistency, navigability, evaluation)\n## MAGIC overview and four-stage pipeline","[{\"question\":\"What makes multi-scene navigation difficult to author manually?\",\"answer\":\"Each scene must be a coherent, navigable interior, and every portal must match consistent endpoints and transition effects on both sides. Designers must also maintain connectivity by hand while keeping paired portals and doorway clearance consistent across files.\"},{\"question\":\"Which three obstacles does MAGIC target that single-scene methods fail to resolve?\",\"answer\":\"MAGIC addresses cross-scene consistency, in-scene navigability after furnishing, and the evaluation problem—existing metrics do not execute transitions, so broken or mislinked portals can go undetected.\"},{\"question\":\"How does MAGIC ensure that generated transitions actually work and are navigable?\",\"answer\":\"It plans a shared transition-aware intermediate representation, uses a flood-fill validator on a 2D occupancy grid to enforce portal reachability during layout specification, and introduces a transition-focused evaluation agent that runs each transition in play to verify functionality.\"}]",1784202659,28,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"magic-transition-aware-generation-of-navigable-multi-scene-game-worlds-with-large-language-models","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/magic-transition-aware-generation-of-navigable-multi-scene-game-worlds-with-large-language-models/85343/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 makes multi-scene navigation difficult to author manually?","Question",{"text":75,"@type":76},"Each scene must be a coherent, navigable interior, and every portal must match consistent endpoints and transition effects on both sides. Designers must also maintain connectivity by hand while keeping paired portals and doorway clearance consistent across files.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which three obstacles does MAGIC target that single-scene methods fail to resolve?",{"text":80,"@type":76},"MAGIC addresses cross-scene consistency, in-scene navigability after furnishing, and the evaluation problem—existing metrics do not execute transitions, so broken or mislinked portals can go undetected.",{"name":82,"@type":73,"acceptedAnswer":83},"How does MAGIC ensure that generated transitions actually work and are navigable?",{"text":84,"@type":76},"It plans a shared transition-aware intermediate representation, uses a flood-fill validator on a 2D occupancy grid to enforce portal reachability during layout specification, and introduces a transition-focused evaluation agent that runs each transition in play to verify functionality.","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":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]