LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs

TL;DR

This paper introduces TrickCatcher, an LLM-based method for generating test cases to detect elusive bugs in plausible programs, significantly outperforming existing approaches in accuracy and reliability.

Contribution

It presents a novel three-stage LLM-powered approach for bug detection in plausible programs, combining variant generation, input synthesis, and inconsistency detection.

Findings

Achieves higher recall, precision, and F1 scores than baselines.

Effective on both human-written and AI-generated programs.

Demonstrates the potential of LLMs in automated bug detection.

Abstract

Detecting tricky bugs in plausible programs, those that pass existing test suites yet still contain bugs, remains a significant challenge in software testing. To address this problem, we propose TrickCatcher, an LLM-powered approach to generating test cases for uncovering bugs in plausible programs. TrickCatcher operates in three stages: First, it uses an LLM to generate program variants based on the program under test (PUT) and its specification. Second, it employs an LLM to construct an input generator from the specification for producing test inputs. Finally, these inputs are executed on both the PUT and its program variants to detect inconsistencies in their outputs. We evaluate TrickCatcher on two datasets, TrickyBugs and EvalPlus, which include 366 human-written and 151 AI-generated plausible programs with tricky bugs. TrickCatcher achieves recall, precision, and F1 scores that are 1.80x, 2.65x, and 1.66x those of the state-of-the-art baselines, respectively. Code and data used are available at https://github.com/RinCloud/TrickCatcher.