AI-generated content has progressed from monolithic models to modular workflows, especially on platforms like ComfyUI, allowing users to customize complex creative pipelines. However, the large number of components in ComfyUI and the difficulty of maintaining long-horizon structural consistency under strict graph constraints frequently lead to low pass rates and workflows of limited quality. To tackle these limitations, we present ComfySearch, an agentic framework that can effectively explore the component space and generate functional ComfyUI pipelines via validation-guided workflow construction. Experiments demonstrate that ComfySearch substantially outperforms existing methods on complex and creative tasks, achieving higher executability (pass) rates, higher solution rates, and stronger generalization.

翻译：AI生成内容已从单一模型发展为模块化工作流，尤其是在ComfyUI等平台上，用户能够定制复杂的创意流程。然而，ComfyUI中组件数量庞大，且在严格的图结构约束下难以保持长时程结构一致性，这常常导致流程通过率低且生成质量有限。为应对这些局限，我们提出ComfySearch——一种能够有效探索组件空间，并通过验证引导的工作流构建生成功能性ComfyUI管线的智能体框架。实验表明，在复杂创意任务中，ComfySearch显著优于现有方法，实现了更高的可执行（通过）率、更高的问题解决率以及更强的泛化能力。