[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82337-en":3,"doc-seo-82337-105":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},82337,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Fictional Worldbuilding Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review","Fictional worldbuilding constructs coherent imaginary universes used in game design and literary creation, yet automated generation struggles with context explosion, the trade-off between creative diversity and global consistency, and the lack of automated quality assurance. The paper introduces AutoWorldBuilder, a multi-agent system combining a structured concept network with conflict detection, semantic-locality-aware scheduling, four-layer hierarchical context compression with ~90% token reduction, and iterative Auditor-based review that increases acceptance from 42% to 85%+. Experiments on 20 tasks using GPT-OSS 120B and DeepSeek v3.2 achieve a 95.0% success rate.","arXiv :2607 .09403v 1 [ cs .AI] 10 Jul 2026  \nFictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review  \nJINGBO CHEN∗ , National University of Defense Technology, China HE WANG†, National University of Defense Technology, China WEI YUAN‡, National University of Defense Technology, China YUQIAO LAI § , National University of Defense Technology, China ZHENYAN LU¶ , National University of Defense Technology, China  \nWorldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Language Models (LLMs) offer new possibilities for automated content generation, but their application to worldbuilding faces three challenges: context explosion that grows linearly with the building process, the tension between creative diversity and content consistency, and the absence of automated quality assurance.  \nThis paper presents AutoWorldBuilder, a multi-agent collaborative system that addresses these challenges through five integrated components: a structured concept network with conflict detection; a DAG-based hybrid batch scheduler that groups tasks by semantic locality; a four-layer context compression mechanism achieving approximately 90% token reduction; an iterative review system with specialized Auditor agents that improves proposal pass rates from 42% to over 85%; anda skill-driven agent architecture supporting zero-code extension with differentiated temperature configuration.  \nTwo experiments across 20 diverse worldbuilding tasks, using GPT-OSS 120B and DeepSeek v3.2 as LLM backends, demonstrate a 95.0% success rate. The system generated 56–103 self-consistent concepts per world in 18–31 minutes, with no conflicts detected by the review pipeline. The architectural patterns validated here, including layer-as-budget compression, semantic-locality scheduling, and separation of generation and review, may transfer to the broader class of knowledgeintensive, multi-agent LLM applications.  \nJAIR Associate Editor:  \nJAIR Reference Format:  \nJingbo Chen, He Wang, Wei Yuan, Yuqiao Lai, and Zhenyan Lu. 2026. Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review. Journal of Artificial Intelligence Research 4, Article 6 (August 2026), 36 pages. doi: 10.1613/jair.1.xxxxx  \n∗ author1 .  \n†author2 .  \n‡Corresponding Author.  \n§ author3 .  \n¶ author4 .  \nAuthors’ Contact Information: Jingbo Chen, oRcid: 0009-0005-5177-5513, [chenjingbo@nudt.edu.cn](chenjingbo@nudt.edu.cn), National University of Defense Technology, Nanjing, Jiangsu, China; He Wang, oRcid: 0009-0009-1274-8319, [wanghe24@nudt.edu.cn](wanghe24@nudt.edu.cn), National University of Defense Technology, Nanjing, Jiangsu, China; Wei Yuan, oRcid: 0009-0004-2498-9447, [yw5811827@126.com](yw5811827@126.com), National University of Defense Technology, Nanjing, Jiangsu, China; Yuqiao Lai, oRcid: 0009-0006-9937-1232, [laiyuqiao24@nudt.edu.cn](laiyuqiao24@nudt.edu.cn), National University of Defense Technology, Nanjing, Jiangsu, China; Zhenyan Lu, oRcid: 0009-0000-9126-7840, [lzy_25@nudt.edu.cn](lzy_25@nudt.edu.cn), National University of Defense Technology, Nanjing, Jiangsu, China.  \nThis work is licensed under a Creative Commons Attribution International 4 .0 License.  \n© 2026 Copyright held by the owner/author(s) .  \ndoi: 10.1613/jair.1.xxxxx  \nJournal of Artificial Intelligence Research, Vol. 4, Article 6 . Publication date: August 2026 .  \n6:2 • Chen  \n1 Introduction  \n1.1 Background and Motivation  \nWorldbuilding, the construction of coherent fictional worlds, is a foundational task in creative content production, including game design, literary creation, film and television production, and tabletop role-playing games (TRPGs) . A complete, self-consistent fictional world typically encompasses multiple dimensions, including geography, intelligent races, magic or technology systems, social organizations, historical","cbCaingvpEczMfyC","https://ap.wps.com/l/cbCaingvpEczMfyC","pdf",912184,2,1,36,"English","en",105,"# Introduction\n## Background and Motivation\n## Core Technical Challenges\n# AutoWorldBuilder System Components","[{\"question\":\"What are the main technical challenges AutoWorldBuilder targets in worldbuilding with LLMs?\",\"answer\":\"It addresses context explosion, inconsistencies between creative diversity and content coherence, and the absence of automated quality assurance for generated content.\"},{\"question\":\"How does AutoWorldBuilder reduce context size during incremental world construction?\",\"answer\":\"It uses a four-layer hierarchical context compression mechanism that achieves about 90% token reduction.\"},{\"question\":\"How does the iterative review system improve the quality of generated world proposals?\",\"answer\":\"Specialized Auditor agents run iterative review, increasing proposal pass rates from 42% to over 85% by detecting issues before acceptance.\"}]",1784179731,91,{"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},"fictional-worldbuilding-multi-agent-llm-collaboration-with-hierarchical-context-compression-and-iterative-review","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/fictional-worldbuilding-multi-agent-llm-collaboration-with-hierarchical-context-compression-and-iterative-review/82337/",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","2026-07-19","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 are the main technical challenges AutoWorldBuilder targets in worldbuilding with LLMs?","Question",{"text":75,"@type":76},"It addresses context explosion, inconsistencies between creative diversity and content coherence, and the absence of automated quality assurance for generated content.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AutoWorldBuilder reduce context size during incremental world construction?",{"text":80,"@type":76},"It uses a four-layer hierarchical context compression mechanism that achieves about 90% token reduction.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the iterative review system improve the quality of generated world proposals?",{"text":84,"@type":76},"Specialized Auditor agents run iterative review, increasing proposal pass rates from 42% to over 85% by detecting issues before acceptance.","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":20,"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":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]