COMFYCLAW：面向图像生成工作流的自进化技能工具包
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
AI总结：
提出COMFYCLAW框架，通过类型化图编辑、区域级VLM验证器和渐进式技能库进化，提升ComfyUI工作流构建的代理可靠性和性能，在多个基准上取得最佳平均评分。
摘要：
代理越来越多地被用于构建工作流，并帮助人类更高效地完成重复性任务。随着这些工作流变得重复且领域特定，代理记忆和可重用技能变得越来越重要：代理应能从前序运行中回忆工作流模式、执行约束和用户偏好。我们在基于工作流的图像生成中研究这一问题，并引入COMFYCLAW，一个用于控制ComfyUI工作流的代理技能进化工具包。COMFYCLAW将工作流构建形式化为类型化图编辑，按构建阶段组织暴露工具，自动回滚无效编辑，并使用区域级视觉语言模型（VLM）验证器将视觉失败转化为可操作的修复建议。该框架进一步进化一个逐步公开的技能库，其中前序运行中的轨迹、执行错误和验证器反馈被提炼为可重用的代理技能。在四个基准划分、三个代理模型和两个图像骨干网络上，COMFYCLAW在所有六个代理配置中取得了最佳平均图像生成评估分数，优于没有技能进化的纯验证器基线。人工注释进一步显示，注释者更偏好COMFYCLAW而非没有技能进化的变体。我们的结果表明，技能进化是提高代理在重复视觉工作流构建中可靠性和性能的有效机制。
英文摘要：
Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently. As these workflows become repeated and domain-specific, agent memory and reusable skills become increasingly important: agents should be able to recall workflow patterns, execution constraints, and user preferences from previous runs. We study this problem in workflow-based image generation and introduce COMFYCLAW, an agentic skill evolution harness for controlling ComfyUI workflows. COMFYCLAW formulates workflow construction as typed graph editing, exposes tools organized by construction stage, automatically reverts invalid edits, and uses a region-level vision-language model (VLM) verifier to translate visual failures into actionable repair suggestions. The framework further evolves a progressively disclosed skill library, where trajectories, execution errors, and verifier feedback from previous runs are distilled into reusable Agent Skills. Across four benchmark splits, three agent models, and two image backbones, COMFYCLAW achieves the best average image-generation evaluation score across all six agent configurations, outperforming a verifier-only baseline without skill evolution. Human annotations further show that annotators prefer COMFYCLAW over variants without skill evolution. Our results suggest that skill evolution is an effective mechanism for improving agent reliability and performance in recurring visual workflow construction.
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。
