Autonomous Agents in Software Development: A Vision Paper

TL;DR

This paper envisions leveraging multiple GPT-based agents to enhance various software engineering tasks, including project planning and design, demonstrating initial promising results in code quality and documentation for simple projects.

Contribution

It proposes a novel approach of using multiple GPT agents for diverse SE tasks and provides an initial experimental analysis supporting its potential.

Findings

Multiple GPT agents can generate high-quality code and documentation.

Initial experiments on simple projects show promising results.

The approach could significantly reduce development lead-times.

Abstract

Large Language Models (LLM) and Generative Pre-trained Transformers (GPT), are reshaping the field of Software Engineering (SE). They enable innovative methods for executing many software engineering tasks, including automated code generation, debugging, maintenance, etc. However, only a limited number of existing works have thoroughly explored the potential of GPT agents in SE. This vision paper inquires about the role of GPT-based agents in SE. Our vision is to leverage the capabilities of multiple GPT agents to contribute to SE tasks and to propose an initial road map for future work. We argue that multiple GPT agents can perform creative and demanding tasks far beyond coding and debugging. GPT agents can also do project planning, requirements engineering, and software design. These can be done through high-level descriptions given by the human developer. We have shown in our initial experimental analysis for simple software (e.g., Snake Game, Tic-Tac-Toe, Notepad) that multiple GPT agents can produce high-quality code and document it carefully. We argue that it shows a promise of unforeseen efficiency and will dramatically reduce lead-times. To this end, we intend to expand our efforts to understand how we can scale these autonomous capabilities further.