AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
This addresses software engineering efficiency for developers by organizing work into sprints, though it appears incremental as it builds on existing multi-agent frameworks.
The authors tackled the problem of oversimplified software development workflows by proposing AgileCoder, a multi-agent system that integrates Agile Methodology with dynamic code graphs, resulting in surpassing benchmarks like ChatDev and MetaGPT to set a new standard.
Software agents have emerged as promising tools for addressing complex software engineering tasks. Existing works, on the other hand, frequently oversimplify software development workflows, despite the fact that such workflows are typically more complex in the real world. 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.