Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs

TL;DR

This paper presents a lifecycle-aware framework for code generation using LLMs that incorporates software engineering phases, intermediate artifacts, and multi-step reasoning, significantly improving code correctness and performance.

Contribution

It introduces a structured, lifecycle-aware approach to LLM-based code generation that leverages intermediate artifacts and multi-step inference, enhancing accuracy and robustness.

Findings

Code correctness improved by up to 75% after fine-tuning.

Multi-step inference outperforms single-step generation.

Open-source LLMs match or outperform pretrained models after fine-tuning.

Abstract

Recent progress in large language models (LLMs) has advanced automatic code generation, yet most approaches rely on direct, single-step translation from problem descriptions to code, disregarding structured software engineering practices. We introduce a lifecycle-aware framework that systematically incorporates intermediate artifacts such as requirements analysis, state machine modeling, and pseudocode into both the training and inference stages. This design aligns code generation with standard software development phases and enables more structured reasoning. Experiments show that lifecycle-level fine-tuning improves code correctness by up to 75% over the same model before fine-tuning, with performance gains compounding across intermediate stages. Multi-step inference consistently surpasses single-step generation, demonstrating the effectiveness of intermediate scaffolding. Notably, open-source LLMs, once fine-tuned under our framework, match or slightly outperform models pretrained on code. When applied to DeepSeek-Coder-1.3B, our framework yields relative CodeBLEU improvements of 34.3%, 20.0%, 11.2%, and 22.3% over ChatGPT-3.5, ChatGPT-4o-mini, DeepSeek-R1, and LLaMA-8B, respectively. Our pipeline also proves robust with up to 80\% less training data, confirming its resilience. Ablation studies further reveal that each intermediate artifact contributes distinctly to final code quality, with state machine modeling yielding the most substantial impact. Our source code and detailed experimental data are available at https://anonymous.4open.science/r/Lifecycle-Aware-3CCB.