Large Language Models (LLMs) have made significant contributions to software engineering, particularly in the field of code generation, demonstrating the ability to produce functionally correct code snippets. The development of these models involves multiple stages, including pre-training on large amounts of source code data and aligning them with human preferences using various techniques. However, their development process often neglects foundational software engineering (SE) practices and principles. Specifically, LLMs receive limited exposure to core SE concepts during training, such as modularity, single responsibility, cohesion, and coupling. As a result, the generated code may lack the properties critical for building maintainable, extensible, and robust software systems.

This vision paper advocates integrating SE knowledge directly into LLMs to enhance their capability to generate code and SE artifacts that adhere to and align with established best practices. We propose a new direction for LLMs to move beyond their current focus on functional accuracy toward producing robust, maintainable software. To assess how well LLMs internalize SE knowledge, we propose adopting Bloom’s Taxonomy as a comprehensive assessment framework, offering a structured alternative to limited evaluation methods such as probing. By embedding software engineering principles, next-generation LLMs can leverage decades of software engineering knowledge and transform software development with reliable, high-quality generative capabilities.