🎬 One Sentence, One Drama: turn a single sentence into a fully produced short drama!<br>A hierarchical multi-agent framework with three key ingredients:<br>1️⃣ Multi-agent debate for story generation — enforces short-drama pacing &amp; narrative coherence (strong hooks, escalation, satisfying endings)<br>2️⃣ 3D-grounded first-frame generation — keeps characters &amp; scene layouts spatially consistent across clips<br>3️⃣ Multi-stage reviewer loops — automatic error detection &amp; targeted revision across script, visual, and video stages<br>Plus scene-level BGM matching &amp; transition planning for a more immersive watch. We also release Short-Drama-Bench, a benchmark with short-drama-specific metrics. Outperforms existing pipelines on narrative quality, cross-clip consistency, and overall viewing experience. 🚀</p>\n","updatedAt":"2026-05-22T04:39:04.586Z","author":{"_id":"63be636387619d1458c2e8e0","avatarUrl":"/avatars/83e14735760c5cadd5341ebcb4cf9556.svg","fullname":"SHI YUFEI","name":"Master-Shi","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8288130164146423},"editors":["Master-Shi"],"editorAvatarUrls":["/avatars/83e14735760c5cadd5341ebcb4cf9556.svg"],"reactions":[{"reaction":"🔥","users":["DavidYan2001","Master-Shi"],"count":2}],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.22144","authors":[{"_id":"6a0fdc70a53a61ce2e422d8b","name":"Yufei Shi","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d8c","name":"Weilong Yan","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d8d","name":"Naixuan Huang","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d8e","name":"Yucheng Chen","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d8f","name":"Chenyu Zhang","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d90","name":"Tao He","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d91","name":"Si Yong Yeo","hidden":false},{"_id":"6a0fdc70a53a61ce2e422d92","name":"Ming Li","hidden":false}],"publishedAt":"2026-05-21T00:00:00.000Z","submittedOnDailyAt":"2026-05-22T00:00:00.000Z","title":"One Sentence, One Drama: Personalized Short-Form Drama Generation via Multi-Agent Systems","submittedOnDailyBy":{"_id":"63be636387619d1458c2e8e0","avatarUrl":"/avatars/83e14735760c5cadd5341ebcb4cf9556.svg","isPro":false,"fullname":"SHI YUFEI","user":"Master-Shi","type":"user","name":"Master-Shi"},"summary":"Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail to satisfy three key requirements of short-drama generation: (1) narrative pacing, resulting in weak hooks, insufficient escalation, and unattractive endings; (2) spatial consistency, leading to drifting scene layouts and inconsistent character positions across clips; and (3) production-level quality control, requiring extensive manual review and correction across script and visual stages. We present One Sentence, One Drama, a hierarchical multi-agent framework that transforms a user's single-sentence idea into a fully produced short drama through structured intermediate modules and iterative refinement. Our approach is built upon three key components: (1) a multi-agent debate-based story generation module that enforces short-drama pacing and narrative coherence; (2) a 3D-grounded first-frame generation mechanism that establishes a shared spatial reference for consistent character positioning and scene layout across clips; and (3) multi-stage reviewer loops that perform comprehensive error detection and targeted revision across script, visual, and video generation stages. We also introduce scene-level BGM matching and scene transition planning to improve the audience's immersive experience. To systematically evaluate this task, we introduce Short-Drama-Bench, a benchmark that extends standard video quality metrics with short-drama-specific criteria. Experimental results demonstrate that our method significantly outperforms existing pipelines in narrative quality, cross-clip consistency, and overall viewing experience.","upvotes":7,"discussionId":"6a0fdc71a53a61ce2e422d93","ai_summary":"A hierarchical multi-agent framework generates short dramas from single sentences by enforcing narrative pacing, ensuring spatial consistency, and implementing quality control through iterative refinement and reviewer loops.","ai_keywords":["multi-agent framework","narrative pacing","spatial consistency","production-level quality control","story generation module","3D-grounded first-frame generation","multi-stage reviewer loops","scene-level BGM matching","scene transition planning","Short-Drama-Bench"],"organization":{"_id":"6508b28cf36bb51c50faad98","name":"NanyangTechnologicalUniversity","fullname":"Nanyang Technological University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/630ca0817dacb93b33506ce7/ZPD1fvei0bcIGeDXxeSkn.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"668192a3f35c3ff47a8438ee","avatarUrl":"/avatars/6b293341f5dc51f574252c6f57cfd293.svg","isPro":false,"fullname":"Weilong Yan","user":"DavidYan2001","type":"user"},{"_id":"63be636387619d1458c2e8e0","avatarUrl":"/avatars/83e14735760c5cadd5341ebcb4cf9556.svg","isPro":false,"fullname":"SHI YUFEI","user":"Master-Shi","type":"user"},{"_id":"69a3f44f3b6bc387b8d9bb13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/Cmy0aN72dESzT7OhUevyr.jpeg","isPro":false,"fullname":"马 奕辰","user":"chloe-gonzalez2","type":"user"},{"_id":"678b5f27ff9242f6ac71e495","avatarUrl":"/avatars/45b07ebecefcaa3be36c3ae13c8039db.svg","isPro":false,"fullname":"Yucheng Chen","user":"yuchengc","type":"user"},{"_id":"68a430e4c4f2e70a1c06ce29","avatarUrl":"/avatars/a3e63ecfd8f785d69467ab2cd74ee946.svg","isPro":false,"fullname":"HUANG NAIXUAN","user":"NathanHwang","type":"user"},{"_id":"6570450a78d7aca0c361a177","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6570450a78d7aca0c361a177/MX7jHhTQwLs-BvYIu5rqb.jpeg","isPro":false,"fullname":"Harold Chen","user":"Harold328","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6508b28cf36bb51c50faad98","name":"NanyangTechnologicalUniversity","fullname":"Nanyang Technological University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/630ca0817dacb93b33506ce7/ZPD1fvei0bcIGeDXxeSkn.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.22144.md"}">

Get this paper in your agent:

Don't have the latest CLI?

Cite arxiv.org/abs/2605.22144 in a model README.md to link it from this page.

Cite arxiv.org/abs/2605.22144 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2605.22144 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.