ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917188500193280 |
|---|---|
| author | Su, Jinwei Lan, Qizhen Wang, Zeyu Xia, Yinghui Wen, Hairu Duan, Yiqun Xiao, Xi Shi, Tianyu Jingsong, Yang He, Lewei |
| author_facet | Su, Jinwei Lan, Qizhen Wang, Zeyu Xia, Yinghui Wen, Hairu Duan, Yiqun Xiao, Xi Shi, Tianyu Jingsong, Yang He, Lewei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04060 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows Su, Jinwei Lan, Qizhen Wang, Zeyu Xia, Yinghui Wen, Hairu Duan, Yiqun Xiao, Xi Shi, Tianyu Jingsong, Yang He, Lewei Artificial Intelligence 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. |
| title | ComfySearch: Autonomous Exploration and Reasoning for ComfyUI Workflows |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.04060 |