A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm

TL;DR

This paper introduces Neurosymbolic Software Engineering (NSE), a hybrid paradigm combining neural learning and symbolic reasoning with controlled chaos to improve efficiency, transparency, and adaptability in AI-driven software engineering.

Contribution

It proposes a novel neurosymbolic approach that integrates rule-based reasoning with neural models and controlled randomness to address limitations of current large code models.

Findings

Enhances efficiency and transparency in software engineering automation.

Improves adaptability to evolving requirements and unpredictable behaviors.

Lays the foundation for more reliable and interpretable AI-driven SE solutions.

Abstract

The emergence of Large Code Models (LCMs) has transformed software engineering (SE) automation, driving significant advancements in tasks such as code generation, source code documentation, code review, and bug fixing. However, these advancements come with trade-offs: achieving high performance often entails exponential computational costs, reduced interpretability, and an increasing dependence on data-intensive models with hundreds of billions of parameters. In this paper, we propose Neurosymbolic Software Engineering, in short NSE, as a promising paradigm combining neural learning with symbolic (rule-based) reasoning, while strategically introducing a controlled source of chaos to simulate the complex dynamics of real-world software systems. This hybrid methodology aims to enhance efficiency, reliability, and transparency in AI-driven software engineering while introducing controlled randomness to adapt to evolving requirements, unpredictable system behaviors, and non-deterministic execution environments. By redefining the core principles of AI-driven software engineering automation, NSE lays the groundwork for solutions that are more adaptable, transparent, and closely aligned with the evolving demands of modern software development practices.