Can We Classify Flaky Tests Using Only Test Code? An LLM-Based Empirical Study

TL;DR

This study investigates whether large language models can classify flaky tests solely based on test code, finding that they perform only marginally better than random guessing and highlighting the need for additional context.

Contribution

The paper empirically evaluates the effectiveness of pre-trained LLMs in classifying flaky tests using only test code, revealing limitations and guiding future research directions.

Findings

LLMs struggle to classify flaky tests from code alone

Best models perform marginally better than random chance

Test code alone often lacks sufficient information for classification

Abstract

Flaky tests yield inconsistent results when they are repeatedly executed on the same code revision. They interfere with automated quality assurance of code changes and hinder efficient software testing. Previous work evaluated approaches to train machine learning models to classify flaky tests based on identifiers in the test code. However, the resulting classifiers have been shown to lack generalizability, hindering their applicability in practical environments. Recently, pre-trained Large Language Models (LLMs) have shown the capability to generalize across various tasks. Thus, they represent a promising approach to address the generalizability problem of previous approaches. In this study, we evaluated three LLMs (two general-purpose models, one code-specific model) using three prompting techniques on two benchmark datasets from prior studies on flaky test classification. Furthermore, we manually investigated 50 samples from the given datasets to determine whether classifying flaky tests based only on test code is feasible for humans. Our findings indicate that LLMs struggle to classify flaky tests given only the test code. The results of our best prompt-model combination were only marginally better than random guessing. In our manual analysis, we found that the test code does not necessarily contain sufficient information for a flakiness classification. Our findings motivate future work to evaluate LLMs for flakiness classification with additional context, for example, using retrieval-augmented generation or agentic AI.