GenAgent：利用自動化工作流程構建協作式人工智慧系統 生成 - ComfyUI案例研究

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

September 2, 2024

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

cs.AI

摘要

先前許多人工智慧研究都專注於開發單一模型，以最大化其智能和能力，主要目標是提升特定任務的表現。相較之下，本文探討一種替代方法：採用工作流程整合模型、資料來源和管道以解決複雜多樣任務的協作人工智慧系統。我們介紹了基於LLM的框架GenAgent，能自動生成複雜工作流程，相較於單一模型具有更大的靈活性和可擴展性。GenAgent的核心創新在於以程式碼表示工作流程，並透過協作代理逐步構建工作流程。我們在ComfyUI平台上實現了GenAgent並提出了一個新的基準OpenComfy。結果表明，GenAgent在執行層和任務層評估中均優於基準方法，顯示其能夠生成具有卓越效能和穩定性的複雜工作流程。

English

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.