AgileCoder：基于敏捷方法论的软件开发动态协作代理

AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology

June 16, 2024

作者: Minh Huynh Nguyen, Thang Phan Chau, Phong X. Nguyen, Nghi D. Q. Bui

cs.AI

摘要

软件代理已经成为解决复杂软件工程任务的有前途的工具。然而，现有的作品通过遵循瀑布模型过分简化了软件开发工作流程。因此，我们提出了AgileCoder，这是一个将敏捷方法论（AM）整合到框架中的多代理系统。该系统将特定的AM角色（如产品经理、开发人员和测试人员）分配给不同的代理，然后这些代理根据用户输入进行协作开发软件。AgileCoder通过将工作组织成冲刺，并专注于通过冲刺逐步开发软件来提高开发效率。此外，我们引入了动态代码图生成器，这是一个模块，会在对代码库进行更新时动态创建代码依赖图。这使代理能够更好地理解代码库，从而在整个软件开发过程中实现更精确的代码生成和修改。AgileCoder超越了现有的基准，如ChatDev和MetaGPT，树立了新的标准，展示了多代理系统在先进软件工程环境中的能力。我们的源代码可以在https://github.com/FSoft-AI4Code/AgileCoder 找到。

English

Software agents have emerged as promising tools for addressing complex software engineering tasks. However, existing works oversimplify software development workflows by following the waterfall model. Thus, we propose AgileCoder, a multi-agent system that integrates Agile Methodology (AM) into the framework. This system assigns specific AM roles such as Product Manager, Developer, and Tester to different agents, who then collaboratively develop software based on user inputs. AgileCoder enhances development efficiency by organizing work into sprints, focusing on incrementally developing software through sprints. Additionally, we introduce Dynamic Code Graph Generator, a module that creates a Code Dependency Graph dynamically as updates are made to the codebase. This allows agents to better comprehend the codebase, leading to more precise code generation and modifications throughout the software development process. AgileCoder surpasses existing benchmarks, like ChatDev and MetaGPT, establishing a new standard and showcasing the capabilities of multi-agent systems in advanced software engineering environments. Our source code can be found at https://github.com/FSoft-AI4Code/AgileCoder.