# Automating Visual Workflows with LLMs
_A new benchmark, Chat2Workflow, reveals LLMs struggle with generating executable visual workflows, despite progress in capturing intent. A significant gap remains for industrial automation._
**Published:** 2026-04-22
**Source:** https://www.startuphub.ai/ai-news/ai-research/2026/automating-visual-workflows-with-llms
---
The industrial adoption of executable visual workflows, prized for their reliability, is currently hobbled by manual engineering. Developers spend considerable time designing, prompting, and iterating on these complex systems, a process ripe for automation.

## Bridging the Gap to Agentic Workflow Generation

To address this, researchers introduce the [Chat2Workflow benchmark](https://arxiv.org/abs/2604.19667v1), a novel dataset comprising real-world business workflows designed for direct deployment on platforms like Dify and Coze. This benchmark serves as a critical tool to investigate the potential of large language models (LLMs) in automating the multi-round interaction required for workflow creation. The goal is to move beyond manual construction towards more autonomous systems.

## The LLM Frontier: Intent vs. Execution

Experimental results reveal a persistent challenge: while state-of-the-art LLMs can grasp high-level user intent, they falter in generating workflows that are consistently correct, stable, and executable. This gap is particularly pronounced when dealing with complex or evolving requirements. The proposed [agentic](/ai-news/technology/2026/cloudflare-builds-the-agentic-cloud) framework shows promise, achieving up to a 5.34% resolve rate gain in handling recurrent execution errors, yet a significant real-world gap remains, underscoring the need for continued advancement in industrial-grade automation.
---
Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.