[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82567-en":3,"doc-seo-82567-105":29,"detail-sidebar-cat-0-en-105":82},{"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":4,"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},82567,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","Long-form story generation with large language models often fails to keep characters consistent and maintain coherent plot lines, especially when multiple characters interact. This work presents Magnet, a multi-agent goal-driven narrative engine that uses persona-grounded character agents operating on a shared world state and evolving story goals. It pairs with Atlas, a graph-based hallucination detection pipeline that compares scene-level world representations across the story. Evaluations show improved coherence and fewer hallucinations than single-model prompting and IBSEN.","arXiv :2607 .009 18v 1 [ cs .CL] 1 Jul 2026  \nFrom Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives  \nAayush Aluru* , Chloe Ho*1 , Muhammad Hammouri2  \nKerry Luo3 , Myra Malik, Ryan Lagasse† Arjun Bahuguna†4 , Vasu Sharma† Pocket FM  \n[aayush.aluru09@gmail.com](aayush.aluru09@gmail.com) , [ch4941@princeton.edu](ch4941@princeton.edu)  \n[hammouri@umich.edu](hammouri@umich.edu) , [kerryluo1@gmail.com](kerryluo1@gmail.com)  \n[arjunbahuguna251@gmail.com](arjunbahuguna251@gmail.com)  \nAbstract  \nAlthough large language models (LLMs) have demonstrated impressive creative fiction generation, they struggle to maintain narrative consistency and coherent plot lines in long-form stories. In this work, we introduce a unified framework for long-form narrative generation and verification. Magnet, a multi-agent goaldriven narrative engine for storytelling, generates stories with persona-grounded character agents that propose actions based on a shared world state and evolving story goals, while Atlas is a graph-based pipeline that compares scene-level world representations across a generated story to detect hallucinations. By evaluating Magnet using an LLM editor, pairwise rubric scoring, and Atlas, we show that our framework produces coherent narratives compared to single-model prompting and IBSEN. At 100 pages, Magnet reduced annotations and hallucinations by 41 and 50%, respectively, compared to the single model baseline and by 34 and 45%, respectively, compared to IBSEN, with pairwise rubric evaluation showing similar results. These results suggest that long-form narratives can emerge from explicit world-state tracking and goal-driven multi-agent generation, providing a foundation for controllable and structurally coherent long-form narrative generation.  \n1 Introduction  \nLarge language models (LLMs) have significantly advanced open-ended text generation, enabling their use for creating character personas and simulating complex interactions Wang et al. (2024b); OpenAI (2024) . Although LLMs have demonstrated strong narrative generation capabilities, they suffer from character inconsistency and plot discontinuity, limiting their ability to create high-quality long-form narratives Lu et al. (2026); Shao et al. (2023); Yao et al. (2019) .  \nThese failures become pronounced in multi-character environments, where LLMs struggle to balance narrative goals and character actions with complex relationships and interactions Park et al. (2023); Gao et al. (2024); Li et al. (2026a) . Recent work, including StoryVerse Wang et al. (2024a), Agents’Room Huot et al. (2025), and IBSEN Han et al. (2024) have explored the use of multi-agent systems in narrative generation, but they continue to rely on textual memory, limiting their ability to generate coherent stories. Lewis et al. (2021); Shinn et al. (2023); Liu et al. (2026); Teleki et al. (2025) .  \n*  \nEqual contribution.  \n1Princeton University.  \n2University of Michigan.  \n3University of Maryland.†Senior author.  \n4Universitat Pompeu Fabra.  \nIn addition to creative content generation, there remains a need to thoroughly evaluate this content. Existing work has made progress on long-form narrative understanding and factuality (Kočiský et al., 2018 ; Kim et al., 2023 ; Sansford et al., 2024 ; Lyu et al., 2025 ; Hamilton et al., 2025 ; Li et al., 2026a; Wu et al., 2025 ; Que et al., 2024) . However, these methods do not provide a framework for identifying hallucinations within long-form generated narratives.  \nIn this work, we introduce Magnet, a multi-agent story generation system to develop coherent long-form narratives and Atlas, a graph-based hallucination evaluation pipeline that identifies inconsistencies by comparing the world state representation of the present scene against those of previous scenes (Tian et al., 2026) . Our work aims to address the research question: Can long-form narratives emerge from interactions between character personas and updating","cbCain3rRPf49xMc","https://ap.wps.com/l/cbCain3rRPf49xMc","pdf",600628,1,22,"English","en",105,"# Abstract\n# Introduction\n# Related Work\n## Multi-Agent Narrative Generation\n## Structured State Tracking","[{\"question\":\"What is Atlas and how does it evaluate hallucinations in generated stories?\",\"answer\":\"Atlas is a graph-based evaluation pipeline that compares scene-level world state representations across a generated story to detect inconsistencies, providing interpretable signals of model failures.\"}]",1784181567,55,{"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":77,"head_meta":79,"extra_data":81,"updated_unix":27},"from-personas-to-plot-character-grounded-multi-agent-story-generation-for-long-form-narratives","",{"@graph":35,"@context":76},[36,53,67],{"@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/from-personas-to-plot-character-grounded-multi-agent-story-generation-for-long-form-narratives/82567/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"What is Atlas and how does it evaluate hallucinations in generated stories?","Question",{"text":74,"@type":75},"Atlas is a graph-based evaluation pipeline that compares scene-level world state representations across a generated story to detect inconsistencies, providing interpretable signals of model failures.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,106,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":45,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general"]