GenRouter: Unified Workflow Routing for Agentic Image Generation
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors noticed that current text-to-image models use the same heavy process for every request, even if some are simple and don't need it. They created GenRouter, a system that figures out the best and most efficient way to handle each request by breaking down workflows into basic parts and choosing the right method. This approach saves a lot of computing power and time while making better pictures. GenRouter also learns from experience to get better at deciding how to route requests without extra training.
text-to-image generationagentic workflowsworkflow routingcompute efficiencydemand profilingexperience matchingPareto filteringzero-shot generalizationvisual alignmentiterative reasoning
Authors
Harold Haodong Chen, Zhiyu Hou, Wen-Jie Shu, Weilin Ruan, Yingjie Xu, Litao Guo, Ying-Cong Chen
Abstract
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.