Agent-Driven Automatic Software Improvement

TL;DR

This research explores deploying LLM-powered agents for automated software maintenance, focusing on iterative learning, error correction, and collaborative frameworks to improve code quality and reliability.

Contribution

It introduces a novel agent-based framework utilizing LLMs for continuous learning and collaborative error correction in automated software improvement.

Findings

Proposes an iterative, agent-driven approach for software maintenance.

Develops a collaborative framework for error correction among agents.

Aims to enhance LLM alignment with software development tasks.

Abstract

With software maintenance accounting for 50% of the cost of developing software, enhancing code quality and reliability has become more critical than ever. In response to this challenge, this doctoral research proposal aims to explore innovative solutions by focusing on the deployment of agents powered by Large Language Models (LLMs) to perform software maintenance tasks. The iterative nature of agents, which allows for continuous learning and adaptation, can help surpass common challenges in code generation. One distinct challenge is the last-mile problems, errors at the final stage of producing functionally and contextually relevant code. Furthermore, this project aims to surpass the inherent limitations of current LLMs in source code through a collaborative framework where agents can correct and learn from each other's errors. We aim to use the iterative feedback in these systems to further fine-tune the LLMs underlying the agents, becoming better aligned to the task of automated software improvement. Our main goal is to achieve a leap forward in the field of automatic software improvement by developing new tools and frameworks that can enhance the efficiency and reliability of software development.