A Path Less Traveled: Reimagining Software Engineering Automation via a Neurosymbolic Paradigm
Antonio Mastropaolo, Denys Poshyvanyk
TL;DR
This paper argues that relying solely on large code models for software engineering automation is unsustainable due to high compute, data, and interpretability costs. It proposes Neurosymbolic Software Engineering (NSE), a hybrid framework that integrates neural probabilistic learning with symbolic reasoning and a chaos-driven component to model real-world uncertainty. NSE aims to deliver interpretable, verifiable, and context-aware automation while reducing dependence on massive data and energy-intensive training. By formalizing a triad of components—probabilistic learning, symbolic reasoning, and controlled chaos—the approach seeks to make AI-driven SE automation more robust, adaptable, and trustworthy in evolving software development environments.
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.