AutoFlow: Automated Workflow Generation for Large Language Model Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zelong, Xu, Shuyuan, Mei, Kai, Hua, Wenyue, Rama, Balaji, Raheja, Om, Wang, Hao, Zhu, He, Zhang, Yongfeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909260558893056
author Li, Zelong
Xu, Shuyuan
Mei, Kai
Hua, Wenyue
Rama, Balaji
Raheja, Om
Wang, Hao
Zhu, He
Zhang, Yongfeng
author_facet Li, Zelong
Xu, Shuyuan
Mei, Kai
Hua, Wenyue
Rama, Balaji
Raheja, Om
Wang, Hao
Zhu, He
Zhang, Yongfeng
contents Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external tools for complex-task solving. To make sure LLM Agents follow an effective and reliable procedure to solve the given task, manually designed workflows are usually used to guide the working mechanism of agents. However, manually designing the workflows requires considerable efforts and domain knowledge, making it difficult to develop and deploy agents on massive scales. To address these issues, we propose AutoFlow, a framework designed to automatically generate workflows for agents to solve complex tasks. AutoFlow takes natural language program as the format of agent workflow and employs a workflow optimization procedure to iteratively optimize the workflow quality. Besides, this work offers two workflow generation methods: fine-tuning-based and in-context-based methods, making the AutoFlow framework applicable to both open-source and closed-source LLMs. Experimental results show that our framework can produce robust and reliable agent workflows. We believe that the automatic generation and interpretation of workflows in natural language represent a promising paradigm for solving complex tasks, particularly with the rapid development of LLMs. The source code of this work is available at https://github.com/agiresearch/AutoFlow.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AutoFlow: Automated Workflow Generation for Large Language Model Agents
Li, Zelong
Xu, Shuyuan
Mei, Kai
Hua, Wenyue
Rama, Balaji
Raheja, Om
Wang, Hao
Zhu, He
Zhang, Yongfeng
Computation and Language
Artificial Intelligence
Machine Learning
Recent advancements in Large Language Models (LLMs) have shown significant progress in understanding complex natural language. One important application of LLM is LLM-based AI Agent, which leverages the ability of LLM as well as external tools for complex-task solving. To make sure LLM Agents follow an effective and reliable procedure to solve the given task, manually designed workflows are usually used to guide the working mechanism of agents. However, manually designing the workflows requires considerable efforts and domain knowledge, making it difficult to develop and deploy agents on massive scales. To address these issues, we propose AutoFlow, a framework designed to automatically generate workflows for agents to solve complex tasks. AutoFlow takes natural language program as the format of agent workflow and employs a workflow optimization procedure to iteratively optimize the workflow quality. Besides, this work offers two workflow generation methods: fine-tuning-based and in-context-based methods, making the AutoFlow framework applicable to both open-source and closed-source LLMs. Experimental results show that our framework can produce robust and reliable agent workflows. We believe that the automatic generation and interpretation of workflows in natural language represent a promising paradigm for solving complex tasks, particularly with the rapid development of LLMs. The source code of this work is available at https://github.com/agiresearch/AutoFlow.
title AutoFlow: Automated Workflow Generation for Large Language Model Agents
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2407.12821