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

TL;DR

AgileCoder is a multi-agent system that incorporates Agile methodology to improve collaborative software development, dynamically managing code dependencies and roles to enhance efficiency and surpass existing benchmarks.

Contribution

This work introduces AgileCoder, a novel multi-agent framework integrating Agile roles and dynamic code graph generation for more realistic and effective software engineering automation.

Findings

Outperforms benchmarks like ChatDev and MetaGPT

Enhances code comprehension through dynamic dependency graphs

Improves development efficiency with role-based collaboration

Abstract

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.