GenAgent: Build Collaborative AI Systems with Automated Workflow
  Generation -- Case Studies on ComfyUI

Xiangyuan Xue; Zeyu Lu; Di Huang; Wanli Ouyang; Lei Bai

返回文献探索

Paper · arXiv 2409.01392

GenAgent: Build Collaborative AI Systems with Automated Workflow Generation -- Case Studies on ComfyUI

Xiangyuan Xue, Zeyu Lu, Di Huang, Wanli Ouyang, Lei Bai

9 upvotesSeptember 2, 2024arXiv 预印本

AI 摘要

GenAgent, an LLM-based framework, generates complex workflows automatically, offering flexibility and scalability, and outperforms baselines in various task evaluations.

LLM-based frameworkcollaborative AI systemsworkflowsComfyUI platformOpenComfy benchmark

Abstract

Much previous AI research has focused on developing monolithic models to maximize their intelligence and capability, with the primary goal of enhancing performance on specific tasks. In contrast, this paper explores an alternative approach: collaborative AI systems that use workflows to integrate models, data sources, and pipelines to solve complex and diverse tasks. We introduce GenAgent, an LLM-based framework that automatically generates complex workflows, offering greater flexibility and scalability compared to monolithic models. The core innovation of GenAgent lies in representing workflows with code, alongside constructing workflows with collaborative agents in a step-by-step manner. We implement GenAgent on the ComfyUI platform and propose a new benchmark, OpenComfy. The results demonstrate that GenAgent outperforms baseline approaches in both run-level and task-level evaluations, showing its capability to generate complex workflows with superior effectiveness and stability.