Hugging Face Daily Papers · · 4 min read

GenRouter: Unified Workflow Routing for Agentic Image Generation

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

\n<li><p><strong>GenCanvas:</strong> The first unified workflow space that standardizes the execution paradigm of agentic image generation. It systematically deconstructs the generative process into universal foundational primitives (<em>e.g.</em>, search, reason, verify, and sketch) and establishes a scalable library of workflow templates.</p>\n</li>\n<li><p><strong>GenRouter:</strong> A dynamic, self-evolving workflow router driven by demand profiling, memory-guided utility matching, and Pareto filtering. It seamlessly pairs diverse heterogeneous prompts with optimal execution plans to balance visual performance and computational cost.</p>\n</li>\n</ul>\n","updatedAt":"2026-08-18T02:34:44.411Z","author":{"_id":"6570450a78d7aca0c361a177","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6570450a78d7aca0c361a177/MX7jHhTQwLs-BvYIu5rqb.jpeg","fullname":"Harold Chen","name":"Harold328","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":10,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8196147680282593},"editors":["Harold328"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6570450a78d7aca0c361a177/MX7jHhTQwLs-BvYIu5rqb.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.16721","authors":[{"_id":"6a83c471675db694db8cd48d","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","name":"Harold328"},"name":"Harold Haodong Chen","status":"claimed_verified","statusLastChangedAt":"2026-08-18T08:45:05.121Z","hidden":false},{"_id":"6a83c471675db694db8cd48e","name":"Zhiyu Hou","hidden":false},{"_id":"6a83c471675db694db8cd48f","name":"Wen-Jie Shu","hidden":false},{"_id":"6a83c471675db694db8cd490","name":"Weilin Ruan","hidden":false},{"_id":"6a83c471675db694db8cd491","name":"Yingjie Xu","hidden":false},{"_id":"6a83c471675db694db8cd492","name":"Litao Guo","hidden":false},{"_id":"6a83c471675db694db8cd493","name":"Ying-Cong Chen","hidden":false}],"publishedAt":"2026-08-17T00:00:00.000Z","submittedOnDailyAt":"2026-08-18T00:00:00.000Z","title":"GenRouter: Unified Workflow Routing for Agentic Image Generation","submittedOnDailyBy":{"_id":"6570450a78d7aca0c361a177","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6570450a78d7aca0c361a177/MX7jHhTQwLs-BvYIu5rqb.jpeg","isPro":false,"fullname":"Harold Chen","user":"Harold328","type":"user","name":"Harold328"},"summary":"The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfilling increasingly intricate user requests. While recent agentic image generation workflows enhance static inference with advanced capabilities like external knowledge retrieval and iterative reasoning, they mostly operate in isolated silos with fixed ``one-size-fits-all\" topologies. This inevitably leads to severe compute-mismatch, where simple queries are forced through computationally heavy pipelines. To bridge this gap, we present GenRouter, the first unified workflow routing framework for agentic image generation. We first formulate GenCanvas, standardizing diverse agentic pipelines into a universal set of foundational primitives and executable templates. Operating over this unified space, GenRouter adaptively routes heterogeneous prompts to their optimal workflows via (i) demand profiling, (ii) experience matching, and (iii) Pareto filtering. Extensive experiments across diverse benchmarks demonstrate that GenRouter achieves superior visual alignment while reducing execution costs by over 95% and latency by 65% compared to heavyweight static pipelines. Furthermore, the system continuously self-evolves via accumulated experience, enabling robust zero-shot generalization that boosts performance and halves computational overhead.","upvotes":17,"discussionId":"6a83c472675db694db8cd494","githubRepo":"https://github.com/EnVision-Research/GenRouter","githubRepoAddedBy":"user","ai_summary":"GenRouter is a unified routing framework that adaptively directs prompts to optimal agentic image-generation workflows, cutting costs and latency while improving visual alignment and enabling continuous self-evolution.","ai_keywords":["agentic image generation","workflow routing","GenRouter","GenCanvas","demand profiling","experience matching","Pareto filtering","zero-shot generalization"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":11},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"674aa9af9494dd9106006c27","avatarUrl":"/avatars/2f04bb009983ec0ade738aa7941cf6dc.svg","isPro":false,"fullname":"Zixin Zhang","user":"zhangzixin02","type":"user"},{"_id":"661e3ac525f93ef52e245f78","avatarUrl":"/avatars/923226a68aa549d66b78cdb81d8b5e16.svg","isPro":false,"fullname":"nullbjj","user":"wenjieshu","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"},{"_id":"6926965987352e7a6d4bef8a","avatarUrl":"/avatars/7e5ef18d2f02e5d99c04d346d9ad35d1.svg","isPro":false,"fullname":"Zhiyu Hou","user":"KevinHuge","type":"user"},{"_id":"6476025bfd4c874fa84b6a28","avatarUrl":"/avatars/b5ca2039731fec9d8e95d6d15b7719f5.svg","isPro":false,"fullname":"litao Guo","user":"Riversideli","type":"user"},{"_id":"66ea643899af9ac3463639b1","avatarUrl":"/avatars/252d470e761a57834dee3dbc60dfefed.svg","isPro":false,"fullname":"Disen Lan","user":"landisen","type":"user"},{"_id":"66dd90188934078387eab1b7","avatarUrl":"/avatars/d03676a051f04b80b2a9caeb61adfcb4.svg","isPro":false,"fullname":"Lynn","user":"HKCLynn","type":"user"},{"_id":"6672f7c82376de4b7ab9fbd5","avatarUrl":"/avatars/60fe64dbe4c814fd8b1df7ce2bebc951.svg","isPro":true,"fullname":"Guo","user":"Rongjin03","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"66864408c1d35ab079488662","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66864408c1d35ab079488662/U-btVsJ65j7m6vFLVIka8.jpeg","isPro":false,"fullname":"Hongfei (Faye) Zhang","user":"FayeHongfeiZhang","type":"user"},{"_id":"66e15e6a9cbd604971999bf2","avatarUrl":"/avatars/dc02874bbe33e33c9f0dad4b40e55e01.svg","isPro":false,"fullname":"Yajing Bai","user":"YajingB","type":"user"},{"_id":"654b153a73416a223f6391b3","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/6xV03M53VJlqryTrBjb2B.jpeg","isPro":false,"fullname":"weilin","user":"rwlinno","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"query":{}}">
Papers
arxiv:2608.16721

GenRouter: Unified Workflow Routing for Agentic Image Generation

Published on Aug 17
· Submitted by
Harold Chen
on Aug 18

Abstract

GenRouter is a unified routing framework that adaptively directs prompts to optimal agentic image-generation workflows, cutting costs and latency while improving visual alignment and enabling continuous self-evolution.

The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfilling increasingly intricate user requests. While recent agentic image generation workflows enhance static inference with advanced capabilities like external knowledge retrieval and iterative reasoning, they mostly operate in isolated silos with fixed ``one-size-fits-all" topologies. This inevitably leads to severe compute-mismatch, where simple queries are forced through computationally heavy pipelines. To bridge this gap, we present GenRouter, the first unified workflow routing framework for agentic image generation. We first formulate GenCanvas, standardizing diverse agentic pipelines into a universal set of foundational primitives and executable templates. Operating over this unified space, GenRouter adaptively routes heterogeneous prompts to their optimal workflows via (i) demand profiling, (ii) experience matching, and (iii) Pareto filtering. Extensive experiments across diverse benchmarks demonstrate that GenRouter achieves superior visual alignment while reducing execution costs by over 95% and latency by 65% compared to heavyweight static pipelines. Furthermore, the system continuously self-evolves via accumulated experience, enabling robust zero-shot generalization that boosts performance and halves computational overhead.

Community

Paper author Paper submitter about 6 hours ago
  • GenCanvas: The first unified workflow space that standardizes the execution paradigm of agentic image generation. It systematically deconstructs the generative process into universal foundational primitives (e.g., search, reason, verify, and sketch) and establishes a scalable library of workflow templates.

  • GenRouter: A dynamic, self-evolving workflow router driven by demand profiling, memory-guided utility matching, and Pareto filtering. It seamlessly pairs diverse heterogeneous prompts with optimal execution plans to balance visual performance and computational cost.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Models citing this paper

No model linking this paper

Cite arxiv.org/abs/2608.16721 in a model README.md to link it from this page.

Datasets citing this paper

No dataset linking this paper

Cite arxiv.org/abs/2608.16721 in a dataset README.md to link it from this page.

Spaces citing this paper

No Space linking this paper

Cite arxiv.org/abs/2608.16721 in a Space README.md to link it from this page.

Collections including this paper

No Collection including this paper

Add this paper to a collection 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.

More from Hugging Face Daily Papers