EvolvingWorld introduces an open-schema framework for long-horizon literary world simulation, enabling characters and world states to evolve together through ongoing interactions. Its benchmark spans 57 books, with 138K+ supervised training samples, 222 test snapshots, and trajectory-level evaluation across 20 metrics.</p>\n","updatedAt":"2026-07-21T05:33:53.572Z","author":{"_id":"66783baec3f824dde8f783ac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66783baec3f824dde8f783ac/oqFYUrgs2vnGRhAMSrQpC.jpeg","fullname":"Jeff","name":"JiayuJeff","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7775856256484985},"editors":["JiayuJeff"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/66783baec3f824dde8f783ac/oqFYUrgs2vnGRhAMSrQpC.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2607.17250","authors":[{"_id":"6a5f01de4fe5d1d13e84ac22","name":"Qing Zong","hidden":false},{"_id":"6a5f01de4fe5d1d13e84ac23","name":"Yue Guo","hidden":false},{"_id":"6a5f01de4fe5d1d13e84ac24","name":"Mengxin Yang","hidden":false},{"_id":"6a5f01de4fe5d1d13e84ac25","name":"Yiwen Guo","hidden":false},{"_id":"6a5f01de4fe5d1d13e84ac26","name":"Yangqiu Song","hidden":false}],"publishedAt":"2026-07-19T00:00:00.000Z","submittedOnDailyAt":"2026-07-21T00:00:00.000Z","title":"EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World","submittedOnDailyBy":{"_id":"66783baec3f824dde8f783ac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66783baec3f824dde8f783ac/oqFYUrgs2vnGRhAMSrQpC.jpeg","isPro":false,"fullname":"Jeff","user":"JiayuJeff","type":"user","name":"JiayuJeff"},"summary":"This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evolve together over time. To address this, EvolvingWorld models literary simulation as a long-horizon process where characters interact, scenes progress, and character and world states are persistently updated. Unlike prior systems relying on fixed schemas, EvolvingWorld adopts an open-schema framework to support simulation across diverse literary worlds. The framework consists of two coupled modules: a Character Agent for multi-character role-play and persistent profile evolution, and an LLM-based World Model for global and location/entity-level state maintenance and scene progression. Based on this architecture, we formulate 7 trainable tasks for scene initialization, interaction generation, and state update. We construct a dataset from 57 books, producing 138,596 supervised training samples and 222 snapshots for testing. Furthermore, we introduce a trajectory-level LLM-as-Judge evaluation protocol spanning 10 dimensions and 20 metrics. Experiments show that EvolvingWorld can improve long-horizon simulation by effectively maintaining persistent, coherent character and world development.","upvotes":40,"discussionId":"6a5f01de4fe5d1d13e84ac27","githubRepo":"https://github.com/HKUST-KnowComp/EvolvingWorld","githubRepoAddedBy":"user","githubStars":1,"organization":{"_id":"66543b6e420092799d2f625c","name":"tencent","fullname":"Tencent","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"66783baec3f824dde8f783ac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66783baec3f824dde8f783ac/oqFYUrgs2vnGRhAMSrQpC.jpeg","isPro":false,"fullname":"Jeff","user":"JiayuJeff","type":"user"},{"_id":"67f11b480eee3976c10fa49a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/CgqZ6B0lR1hBN7AC0nLuX.png","isPro":false,"fullname":"ZHOU Hangan","user":"Sanyiluicarbon","type":"user"},{"_id":"68400c7b50cb0ac62e5fd9f2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68400c7b50cb0ac62e5fd9f2/UqFfQFbFsCxjLIcwIwdFx.png","isPro":false,"fullname":"Qihan Lin","user":"tunaaa126","type":"user"},{"_id":"6789d843c417d858f4fbefb3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/BBq5gEowXVXthEOHSy6AE.png","isPro":false,"fullname":"WANG Rui","user":"Roryaccout","type":"user"},{"_id":"64b2f97434a92b848c7e941e","avatarUrl":"/avatars/c699c50f3b43cd1641469521127753bb.svg","isPro":false,"fullname":"Nagori","user":"MohammedNaeem","type":"user"},{"_id":"6861ed12ca30e7f987978c69","avatarUrl":"/avatars/78d5a86abfb45964f61ded2a67c03c52.svg","isPro":false,"fullname":"yisen gao","user":"Eason-nuo","type":"user"},{"_id":"6724ca32ef6317efeb3b8380","avatarUrl":"/avatars/2d358230d32a5a36d0bf90bdbac87a51.svg","isPro":false,"fullname":"weihao liu","user":"zsdvgse","type":"user"},{"_id":"664d930f4b870dd167473c1c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/664d930f4b870dd167473c1c/TXVEPGvkhftdI_xE1mluu.jpeg","isPro":false,"fullname":"Andy Guan","user":"andytonglove","type":"user"},{"_id":"68313679e85918b23d181d47","avatarUrl":"/avatars/85a7b26564365b88469357ed4adb1b40.svg","isPro":false,"fullname":"Liu Yuxuan","user":"xuansenpai","type":"user"},{"_id":"692f9daa20092e3c4123cd01","avatarUrl":"/avatars/803155f02bae7a099310d7c47016406c.svg","isPro":false,"fullname":"Irene","user":"irenehere","type":"user"},{"_id":"687f853bb39262ba84f3eeff","avatarUrl":"/avatars/cdfc44fde8237f08f10192553fe5a075.svg","isPro":false,"fullname":"Junhao Shen","user":"shenjunhao","type":"user"},{"_id":"6434e2747b824748011030ee","avatarUrl":"/avatars/3f222fd8bff71b007b2b6eccd953b9a9.svg","isPro":false,"fullname":"Hong Ting Tsang","user":"gzone0111","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":2,"organization":{"_id":"66543b6e420092799d2f625c","name":"tencent","fullname":"Tencent","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2607/2607.17250.md","query":{}}">
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
Abstract
This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evolve together over time. To address this, EvolvingWorld models literary simulation as a long-horizon process where characters interact, scenes progress, and character and world states are persistently updated. Unlike prior systems relying on fixed schemas, EvolvingWorld adopts an open-schema framework to support simulation across diverse literary worlds. The framework consists of two coupled modules: a Character Agent for multi-character role-play and persistent profile evolution, and an LLM-based World Model for global and location/entity-level state maintenance and scene progression. Based on this architecture, we formulate 7 trainable tasks for scene initialization, interaction generation, and state update. We construct a dataset from 57 books, producing 138,596 supervised training samples and 222 snapshots for testing. Furthermore, we introduce a trajectory-level LLM-as-Judge evaluation protocol spanning 10 dimensions and 20 metrics. Experiments show that EvolvingWorld can improve long-horizon simulation by effectively maintaining persistent, coherent character and world development.
Community
EvolvingWorld introduces an open-schema framework for long-horizon literary world simulation, enabling characters and world states to evolve together through ongoing interactions. Its benchmark spans 57 books, with 138K+ supervised training samples, 222 test snapshots, and trajectory-level evaluation across 20 metrics.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2607.17250 in a model README.md to link it from this page.
Cite arxiv.org/abs/2607.17250 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2607.17250 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.