ComfySearch: 为ComfyUI工作流实现自主探索与推理
ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows
AI总结：
ComfySearch通过验证引导的工作流构建，有效提升ComfyUI工作流的通过率和解决方案率，适用于复杂创意任务。
摘要：
AI生成内容已从单体模型发展到模块化工作流，尤其是在ComfyUI等平台上，允许用户自定义复杂的创意管道。然而，ComfyUI中大量组件的数量以及在严格图约束下维持长周期结构一致性方面的难度，常常导致低通过率和低质量的工作流。为解决这些限制，我们提出了ComfySearch，一个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ComfyUI管道的代理框架。实验表明，ComfySearch在复杂和创意任务上显著优于现有方法，实现了更高的可执行性（通过率）、更高的解决方案率和更强的泛化能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
