Variability-Aware Detection and Repair of Compilation Errors Using Foundation Models in Configurable Systems

TL;DR

This study demonstrates that foundation models like GPT-OSS-20B can effectively detect and repair variability-induced compilation errors in configurable C systems, outperforming traditional tools and offering a practical low-effort solution.

Contribution

It introduces the use of foundation models for variability-aware detection and repair of compilation errors, showing their effectiveness compared to existing variability-aware tools.

Findings

Foundation models achieve high precision and recall in detecting errors.

GPT-OSS-20B repairs over 70% of compilation errors successfully.

Models detect real-world faults and identify potential bugs in large codebases.

Abstract

Modern software systems often rely on conditional compilation to support optional features and multiple deployment scenarios. In configurable systems, compilation errors may arise only under specific combinations of features, remaining hidden during development and testing. Such variability-induced errors are difficult to detect in practice, as traditional compilers analyze only a single configuration at a time, while existing variability-aware tools typically require complex setup and incur high analysis costs. In this article, we present an empirical study on the use of foundation models to detect and fix compilation errors caused by feature variability in configurable C systems. We evaluate GPT-OSS-20B and GEMINI 3 PRO, and compare them with TYPECHEF, a state-of-the-art variability-aware parser. Our evaluation considers two complementary settings: 5,000 small configurable systems designed to systematically exercise variability-induced compilation behavior, comprising both systems with and without compilation errors, and 14 real-world GitHub commits, as well as an additional set of mutation testing scenarios (42). Our results show that foundation models can effectively identify variability-induced compilation errors. On small configurable systems, GPT-OSS-20B achieved a precision of 0.97, recall of 0.90, and accuracy of 0.94, substantially increasing detection coverage compared to TYPECHEF, and exhibiting performance comparable to GEMINI 3. For compilation error repair, GPT-OSS-20B produced compilable fixes in over 70% of the cases. In the analysis of real commits, CHATGPT-5.2 detected all injected faults except for two cases and identified a potential real compilation bug in a Linux commit with more than 1,000 modified lines. Our findings indicate that current state-of-the-art foundation models provide a practical and low-effort complement to traditional variability-aware analyses.