{"title":"流程上的思考:多代理系统协作开发的动态流程生成","authors":"Leilei Lin, Yingming Zhou, Wenlong Chen, Chen Qian","doi":"arxiv-2409.06568","DOIUrl":null,"url":null,"abstract":"Software development is a collaborative endeavor that requires individuals\nfrom different departments to work together in order to collectively develop a\nhigh-quality software system. In this context, people have begun to explore a\nmethod that leverages multi-agent systems based on LLMs to carry out software\ndevelopment. However, existing research tends to rigidly fix the software\ndevelopment process in a framework in code form, thus failing to dynamically\nadjust the software development process in real-time to meet the more flexible\nand variable software environment. In this paper, we propose a dynamic process\ngeneration framework, named ToP (Think-on-Process). The core idea of ToP is to\nleverage experiential knowledge (i.e., process models) to guide LLMs in\ngenerating software development processes (i.e., instances). These instances\nwill guide multi-agent in software development and employ a compiler to provide\nfeedback on the development outcomes. Subsequently, we utilize heuristic\nalgorithms to filter the instances and apply process mining algorithms to\nderive process model. Finally, the process model will be converted into text,\nformatted as prompts, to enhance the ability of LLMs to generate other\ninstances. Experiments demonstrate that our framework ToP significantly\nenhances the dynamic process generation capability of the GPT-3.5 and GPT-4 for\nfive categories of software development tasks.","PeriodicalId":501278,"journal":{"name":"arXiv - CS - Software Engineering","volume":"95 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Think-on-Process: Dynamic Process Generation for Collaborative Development of Multi-Agent System\",\"authors\":\"Leilei Lin, Yingming Zhou, Wenlong Chen, Chen Qian\",\"doi\":\"arxiv-2409.06568\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Software development is a collaborative endeavor that requires individuals\\nfrom different departments to work together in order to collectively develop a\\nhigh-quality software system. In this context, people have begun to explore a\\nmethod that leverages multi-agent systems based on LLMs to carry out software\\ndevelopment. However, existing research tends to rigidly fix the software\\ndevelopment process in a framework in code form, thus failing to dynamically\\nadjust the software development process in real-time to meet the more flexible\\nand variable software environment. In this paper, we propose a dynamic process\\ngeneration framework, named ToP (Think-on-Process). The core idea of ToP is to\\nleverage experiential knowledge (i.e., process models) to guide LLMs in\\ngenerating software development processes (i.e., instances). These instances\\nwill guide multi-agent in software development and employ a compiler to provide\\nfeedback on the development outcomes. Subsequently, we utilize heuristic\\nalgorithms to filter the instances and apply process mining algorithms to\\nderive process model. Finally, the process model will be converted into text,\\nformatted as prompts, to enhance the ability of LLMs to generate other\\ninstances. Experiments demonstrate that our framework ToP significantly\\nenhances the dynamic process generation capability of the GPT-3.5 and GPT-4 for\\nfive categories of software development tasks.\",\"PeriodicalId\":501278,\"journal\":{\"name\":\"arXiv - CS - Software Engineering\",\"volume\":\"95 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Software Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.06568\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Software Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06568","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Think-on-Process: Dynamic Process Generation for Collaborative Development of Multi-Agent System
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.