arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.25928cs.SE
收藏

自主多智能体系统用于连续软件开发

TheBotCompany: Self-Organizing Multi-agent Systems for Continuous Software Development

William & Mary(威廉与玛丽学院)

Wenhan Lyu, Yue Xiao, Yixuan Zhang, Yifan Sun

AI总结:

本文提出TheBotCompany框架,通过三阶段状态机、自组织智能体团队和异步人类监督,实现持续软件开发的自动化与长期进展。

摘要:

基于大语言模型的多智能体系统在自动化软件开发任务中展现出潜力。然而,大多数系统专注于完成小型任务和增量代码更改,持续软件开发仍被忽视。我们提出了TheBotCompany,一个开源的持续多智能体软件开发编排框架。TheBotCompany引入三个关键创新:(1)三阶段状态机(策略到执行到验证)用于里程碑驱动开发;(2)自组织智能体团队,其中管理者智能体根据项目需求动态雇佣、分配和解雇工人智能体;(3)异步人类监督。我们在多个真实软件项目上评估TheBotCompany,持续多天开发,测量团队适应模式、里程碑完成率、成本效率和代码质量。我们的结果表明,自组织方法能够实现有效的长期软件开发,具有可测量的进展,而验证阶段能够捕捉否则会持续存在的缺陷。

英文摘要:

Large language model (LLM)-based multi-agent systems have shown promise in automating software development tasks. However, most vibe-coding systems focus on completing small tasks and incremental code changes, leaving persistent, continuous software development largely unexplored. We present TheBotCompany, an open-source orchestration framework for continuous multi-agent software development. TheBotCompany introduces three key innovations: (1) a three-phase state machine (Strategy to Execution to Verification) for milestone-driven development, (2) self-organizing agent teams where manager agents dynamically hire, assign, and retire worker agents based on project needs, and (3) asynchronous human oversight. We evaluate TheBotCompany on real-world software projects over multiple days of continuous development, measuring team adaptation patterns, milestone completion rates, cost efficiency, and code quality. Our results demonstrate that the self-organizing approach enables effective long-term software development with measurable progress, while the verification phase catches defects that would otherwise persist.

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。

↑