46 citations · 75 across the 13 of their papers we have counts for
10 papers · 1 filter
DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents
Qinghua Xu, Guancheng Wang, Boxi Yu +2
Testing deep reinforcement learning (DRL) agents in cyber-physical systems aims to uncover diverse failures before deployment, but each execution can be expensive. Surrogate-assist…
TATG: Tracking-Aware Testing Objective for LLM-based Test Generation
Guancheng Wang, Qinghua Xu, Lionel C. Briand
Complex Java methods remain challenging for automated unit test generation because achieving high coverage and fault detection often requires satisfying branch-specific testing req…
BeSpec: Behavior-Level Specification Alignment for Code Generation
Qinghua Xu, Guancheng Wang, Boxi Yu +1
LLMs have made substantial progress on automated code generation from natural-language descriptions of desired behavior (intent). Most existing methods improve generated programs t…
LLM-based Low-Level Integration Test Generation for Java
Qinghua Xu, Guancheng Wang, Lionel Briand +2
Large language models (LLMs) show promise for automated test generation, but most approaches target unit tests with mocked dependencies. Low-level integration testing instead exerc…
Call-Chain-Aware LLM-Based Test Generation for Java Projects
Guancheng Wang, Qinghua Xu, Lionel C. Briand +2
Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approaches primarily rely on execution…
SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
Boxi Yu, Yang Cao, Yuzhong Zhang +9
The SWE-Bench Verified leaderboard is approaching saturation, with the top system achieving 78.80%. However, we show that this performance is inflated. Our re-evaluation reveals th…
Mutation-Guided Unit Test Generation with a Large Language Model
Guancheng Wang, Qinghua Xu, Lionel Briand +1
Unit tests play a vital role in uncovering potential faults in software. While tools like EvoSuite focus on maximizing code coverage, recent advances in large language models (LLMs…
Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation
Qinghua Xu, Guancheng Wang, Lionel Briand +1
Unit testing plays a critical role in ensuring software correctness. However, writing unit tests manually is labor-intensive, especially for strongly typed languages like Java, mot…
LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
Fatemeh Hadadi, Qinghua Xu, Domenico Bianculli +1
Most log-based anomaly detectors assume logs are stable, though logs are often unstable due to software or environmental changes. Anomaly detection on unstable logs (ULAD) is there…
Pretrain, Prompt, and Transfer: Evolving Digital Twins for Time-to-Event Analysis in Cyber-physical Systems
Qinghua Xu, Tao Yue, Shaukat Ali +1
Cyber-Physical Systems (CPSs), e.g., elevator systems and autonomous driving systems, are progressively permeating our everyday lives. To ensure their safety, various analyses need…