arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.06568cs.SE
收藏

Think-on-Process:面向多智能体系统协同开发的动态流程生成

Think-on-Process: Dynamic Process Generation for Collaborative Development of Multi-Agent System

Leilei Lin, Yingming Zhou, Wenlong Chen, Chen Qian

AI总结:

本文提出 ToP 动态流程生成框架,通过流程模型指导 LLM 生成开发实例,并结合编译器反馈、启发式筛选与流程挖掘迭代更新模型,显著提升 GPT-3.5/GPT-4 应对五类软件开发任务的能力。

摘要:

软件开发是一项协作性工作,需要来自不同部门的人员共同合作,以集体开发高质量的软件系统。在此背景下,人们已经开始探索利用基于 LLM 的多智能体系统来开展软件开发的方法。然而,现有研究往往以代码形式将软件开发流程刚性地固定在框架中,因而无法实时动态调整软件开发流程,以满足更加灵活多变的软件环境。本文提出一个名为 ToP(Think-on-Process)的动态流程生成框架。ToP 的核心思想是利用经验知识(即流程模型)指导 LLM 生成软件开发流程(即实例)。这些实例将引导多智能体进行软件开发,并使用编译器对开发结果提供反馈。随后,我们利用启发式算法筛选实例,并应用流程挖掘算法推导流程模型。最后,流程模型将被转换为文本并格式化为提示词,以增强 LLM 生成其他实例的能力。实验表明,我们的框架 ToP 在五类软件开发任务上显著提升了 GPT-3.5 和 GPT-4 的动态流程生成能力。

英文摘要:

Software development is a collaborative endeavor that requires individuals from different departments to work together in order to collectively develop a high-quality software system. In this context, people have begun to explore a method that leverages multi-agent systems based on LLMs to carry out software development. However, existing research tends to rigidly fix the software development process in a framework in code form, thus failing to dynamically adjust the software development process in real-time to meet the more flexible and variable software environment. In this paper, we propose a dynamic process generation framework, named ToP (Think-on-Process). The core idea of ToP is to leverage experiential knowledge (i.e., process models) to guide LLMs in generating software development processes (i.e., instances). These instances will guide multi-agent in software development and employ a compiler to provide feedback on the development outcomes. Subsequently, we utilize heuristic algorithms to filter the instances and apply process mining algorithms to derive process model. Finally, the process model will be converted into text, formatted as prompts, to enhance the ability of LLMs to generate other instances. Experiments demonstrate that our framework ToP significantly enhances the dynamic process generation capability of the GPT-3.5 and GPT-4 for five categories of software development tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑