GenRouter: Unified Workflow Routing for Agentic Image Generation

2026-08-17

AI Summary

This study addresses resource misallocation and inefficiency caused by fixed topologies in agent-based image generation by proposing the first unified workflow routing framework. We introduce GenRouter for adaptive routing and GenCanvas for standardized templating, integrated with Pareto filtering and experience matching mechanisms to achieve precise mapping from heterogeneous prompts to optimal workflows with zero-shot generalization. Experimental results demonstrate that this approach significantly enhances visual alignment while reducing execution costs by over 95% and latency by 65%. Furthermore, the framework exhibits continuous self-evolution capabilities, substantially optimizing overall system efficacy and resource utilization compared to existing static architectures.

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.

Problem

• Agentic Image Generation
• Workflow Routing
• Compute-mismatch
• Text-to-Image

Innovation

• Workflow Routing
• Agentic Image Generation
• GenCanvas
• Pareto Filtering
• Self-evolution