2026/04/21 by Yi Zhong, Buqiang Xu, Xu BuQiang +5 · 1 voice
Computer Science · Decision Sciences · Materials Science · #Benchmark (surveying) #Data Visualization and Analytics #Executable #Machine Learning in Materials Science #Natural language #Scientific Computing and Data Management #Semantics (computer science) #Visual language #Workflow #cs.AI #cs.CL #cs.CV #cs.LG #cs.MA
paper · pdf · doi:10.48550/arxiv.2604.19667
openalex publication_date 2026/04/21 · arxiv published 2026/04/21 · openalex created_date 2026/04/23 · arxiv updated 2026/05/26 · openalex updated_date 2026/07/28
At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely constructed through manual engineering: developers must carefully design workflows, write prompts for each step, and repeatedly revise the logic as requirements evolve -- making development costly, time-consuming, and error-prone. To study whether large language models can automate this multi-round interaction process, we introduce Chat2Workflow, a benchmark for generating executable visual workflows directly from natural language, and propose a robust agentic baseline to improve performance. The benchmark is built from a large collection of real-world business workflows, with each instance designed so that the generated workflow can be transformed and directly deployed to practical workflow platforms such as Dify and Coze. Experimental results show that while state-of-the-art language models can often capture high-level intent, they struggle to generate correct, stable, and executable workflows, especially given complex and evolving requirements. Although our agentic baseline yields up to 6.05% resolve rate gains, the remaining real-world gap positions Chat2Workflow as a foundation for advancing industrial-grade automation. Code is available at https://github.com/zjunlp/Chat2Workflow.