arXiv subjects

Qinghua Xu

Publications and source records attributed to Qinghua Xu.

At least 19 recordsLinked to original sources

arXiv2026

LLM-based Low-Level Integration Test Generation for Java

Large language models (LLMs) show promise for automated test generation, but most approaches target unit tests with mocked dependencies. Low-level integration testing instead exercises a class with its real, in-project dependencies, exposing faults involving object construction, API call sequences, and component interactions. Generating such tests is challenging because LLMs may lack project-specific knowledge (not knowing) or violate provided constraints (not following). We present IntTestGen, an LLM-based approach that combines context-enriched generation with constraint-enforced fixing. It mines dependency usage patterns from project code to guide test generation, then applies symbol-, protocol-, and iteration-level constraints during repair using a ClassIndex, a Markov typestate model, and experience memory. We evaluate IntTestGen against the state-of-the-art LLM-based baseline PANTA and search-based baseline EvoSuite on Defects4J and Deps4J, a new post-cutoff benchmark of recent Java repositories. Across the two benchmarks, IntTestGen improves line coverage by 19.99 and 22.69 percentage points, branch coverage by 24.90 and 15.78 points, and mutation score by 13.67 and 0.17 points, respectively. It also covers 378 and 55 additional lines of dependency code. Ablation results confirm that all major components contribute to performance.

cs.SE↗

arXiv2026

BeSpec: Behavior-Level Specification Alignment for Code Generation

LLMs have made substantial progress on automated code generation from natural-language descriptions of desired behavior (intent). Most existing methods improve generated programs through execution-guided code refinement: they generate a candidate solution, execute it, and patch the implementation using feedback, while leaving the underlying specification unchanged. This workflow implicitly assumes that the LLM's understanding of the intent is already correct and complete. In practice, however, intents are often ambiguous or underspecified. As a result, even a capable model may produce a correct implementation of the wrong intent, making specification mismatch a central bottleneck. This paper presents BeSpec, a behavioral model-based approach to specification alignment. BeSpec treats the task description as partial evidence about the intended behavior of the correct program. It first builds an explicit behavioral model, which are checkable properties that valid outputs must satisfy. BeSpec then generates candidate programs, executes them on probe inputs, and compares their observed behavior with the predicted behaviors. When observed behavior does not match the predicted behaviors, BeSpec either refines the specification or rejects the candidate program. We evaluate BeSpec with three LLMs on four benchmarks: CodeContests, xCodeEval, APPS, and the contamination-free LiveCodeBench. Against nine baselines, BeSpec achieves the highest Pass@1 and average pass rate across all settings, improving average Pass@1 over the strongest baseline by 8.1%--25.3% relative across the three LLMs. A failure analysis shows that after alignment, most remaining errors stem from algorithmic difficulty rather than misunderstood specifications, while ablation studies confirm that each major component of BeSpec contributes positively.

cs.SE↗

arXiv2026

TATG: Tracking-Aware Testing Objective for LLM-based Test Generation

Complex Java methods remain challenging for automated unit test generation because achieving high coverage and fault detection often requires satisfying branch-specific testing requirements that are not directly visible from a focal method. Recent LLM-based approaches, such as KTester, PANTA, and MUTGEN, leverage project context, static analysis, coverage feedback, or mutation guidance. However, they do not explicitly represent and track individual testing requirements across iterations. As a result, generation may repeatedly target satisfied requirements while overlooking unresolved branches and weak assertions. Existing approaches also optimize structural coverage and mutation effectiveness separately. We present TATG, a tracking-aware LLM-based unit test generation approach. TATG introduces a unified objective representation that captures testing requirements derived from static analysis and dynamic feedback. The representation enables fine-grained tracking of satisfied and unresolved requirements throughout generation. TATG further employs a two-stage workflow: structural rounds improve coverage, followed by mutation-guided hardening rounds that strengthen assertions and improve fault detection. We evaluate TATG on 141 complex Java methods, including the 110 KTester subjects and 31 additional challenging methods. Compared with KTester and PANTA, TATG improves line coverage, branch coverage, and mutation score by 22.15, 20.14, and 37.66 percentage points on average. On a selected subset of focal methods, TATG also achieves performance comparable to a proprietary industrial test generation tool while achieving higher line coverage and mutation score.

cs.SE↗

arXiv2026

Uncertainty-Guided Label Rebalancing for CPS Safety Monitoring

Safety monitoring is essential for Cyber-Physical Systems (CPSs). However, unsafe events are rare in real-world CPS operations, creating an extreme class imbalance that degrades safety predictors. Standard rebalancing techniques perform poorly on time-series CPS telemetry, either generating unrealistic synthetic samples or overfitting on the minority class. Meanwhile, behavioral uncertainty in CPS operations, defined as the degree of doubt or uncertainty in CPS decisions , is often correlated with safety outcomes but unexplored in safety monitoring. To that end, we propose U-Balance, a supervised approach that leverages behavioral uncertainty to rebalance imbalanced datasets prior to training a safety predictor. U-Balance first trains a GatedMLP-based uncertainty predictor that summarizes each telemetry window into distributional kinematic features and outputs an uncertainty score. It then applies an uncertainty-guided label rebalancing (uLNR) mechanism that probabilistically relabels $\textit{safe}$-labeled windows with unusually high uncertainty as $\textit{unsafe}$, thereby enriching the minority class with informative boundary samples without synthesizing new data. Finally, a safety predictor is trained on the rebalanced dataset for safety monitoring. We evaluate U-Balance on a large-scale UAV benchmark with a 46:1 safe-to-unsafe ratio. Results confirm a moderate but significant correlation between behavioral uncertainty and safety. We then identify uLNR as the most effective strategy to exploit uncertainty information, compared to direct early and late fusion. U-Balance achieves a 0.806 F1 score, outperforming the strongest baseline by 14.3 percentage points, while maintaining competitive inference efficiency. Ablation studies confirm that both the GatedMLP-based uncertainty predictor and the uLNR mechanism contribute significantly to U-Balance's effectiveness.

cs.LG↗

arXiv2026

Call-Chain-Aware LLM-Based Test Generation for Java Projects

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-path information to guide prompt construction, which is often insufficient for complex software systems with rich inter-class dependencies, deep call chains, and intricate object initialization requirements. In this paper, we present CAT, a novel call-chain-aware LLM-based test generation approach that explicitly incorporates call-chain and dependency contexts into prompts through dedicated static analysis. To construct executable, semantically valid test contexts, CAT systematically models caller--callee relationships, object constructors, and third-party dependencies, and supports iterative test fixing when generation failures occur. We evaluate CAT on the widely used Defects4J benchmark and on four real-world GitHub projects released after the LLM's cut-off date. The results show that, across projects in Defects4J, CAT improves line and branch coverage by 18.04% and 21.74%, respectively, over the state-of-the-art approach PANTA, while consistently achieving superior performance on post-cutoff real-world projects. An ablation study further demonstrates the importance of call-chain and dependency contexts in CAT.

cs.SE↗

arXiv2026

Mutation-Guided Unit Test Generation with a Large Language Model

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) have shifted attention toward LLM-based test generation. However, code coverage metrics -- such as line and branch coverage -- remain overly emphasized in reported research, despite being weak indicators of a test suite's fault-detection capability. In contrast, mutation score offers a more reliable and stringent measure, as demonstrated in our findings where some test suites achieve 100% coverage but only 4% mutation score. Although a few studies consider mutation score, the effectiveness of LLMs in killing mutants remains underexplored. In this paper, we propose MUTGEN, a mutation-guided, LLM-based test generation approach that incorporates mutation feedback directly into the prompt. Evaluated on 204 subjects from two benchmarks, MUTGEN significantly outperforms both EvoSuite and vanilla prompt-based strategies in terms of mutation score. Furthermore, MUTGEN introduces an iterative generation mechanism that pushes the limits of LLMs in killing additional mutants. Our study also provide insights into the limitations of LLM-based generation, analyzing the reasons for live and uncovered mutants, and the impact of different mutation operators on generation effectiveness.

cs.SE↗

arXiv2026

Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation

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, motivating the need for automated approaches. Traditional methods primarily rely on search-based or randomized algorithms to achieve high code coverage and produce regression oracles, which are derived from the program's current behavior rather than its intended functionality. Recent advances in LLMs have enabled oracle generation from natural language descriptions, aligning better with user requirements. However, existing LLM-based methods often require fine-tuning or rely on external tools such as EvoSuite for test prefix generation, making them costly or cumbersome to apply in practice. In this work, we propose CANDOR, a novel prompt engineering-based LLM framework for automated unit test generation in Java. CANDOR orchestrates multiple specialized LLM agents to collaboratively generate complete tests. To mitigate the notorious hallucinations in LLMs and improve oracle correctness, we introduce a novel strategy that engages multiple reasoning LLMs in a panel discussion and generates accurate oracles based on consensus. Additionally, to reduce the verbosity of reasoning LLMs' outputs, we propose a novel dual-LLM pipeline to produce concise and structured oracle evaluations. Our experiments show that CANDOR is comparable with EvoSuite in generating tests with high code coverage and clearly superior in terms of mutation score. Moreover, our prompt engineering-based approach CANDOR significantly outperforms the SOTA fine-tuning-based oracle generator TOGLL by at least 21.1 percentage points in oracle correctness on both correct and faulty source code. Further ablation studies confirm the critical contributions of key agents in generating high-quality tests.

cs.SE↗

arXiv2026

SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark

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 that one in five "solved" patches from the top-30 agents are semantically incorrect, passing only because weak test suites fail to expose their errors. We present SWE-ABS, an adversarial framework that strengthens test suites through a two-stage pipeline: (1) coverage-driven augmentation using program slicing to target untested code regions, and (2) mutation-driven adversarial testing that synthesizes plausible but incorrect patches to expose semantic blind spots. On SWE-Bench Verified (500 instances), SWE-ABS strengthens 50.2% of instances, a 25.1x improvement over prior work, and rejects 19.71% of previously passing patches. As a result, the top agent's score decreases from 78.80% to 62.20%, leading to significant leaderboard reshuffling, with the previous top-ranked agent dropping to fifth place.

cs.SE↗

arXiv2026

Selected highlights from STAR experiment

In this paper, we review recent highlights in heavy-ion collisions and proton-proton collisions at top energies from STAR experiment at the Relativistic Heavy Ion Collider (RHIC) with key contributions from Chinese groups, including the Quark-Gluon Plasma (QGP) bulk properties, electromagnetic probes, heavy flavor and jets, antimatter hyper-nucleus, nuclear structure, global polarization, and nucleon spin structure. These data serve as important ingredients in the physics of Quantum Chromodynamics (QCD).

nucl-ex↗

arXiv2025

LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs

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 therefore a more realistic, yet under-investigated challenge. Current approaches predominantly employ machine learning (ML) models, which often require extensive labeled data for training. To mitigate data insufficiency, we propose FlexLog, a novel hybrid approach for ULAD that combines ML models -- decision tree, k-nearest neighbors, and a feedforward neural network -- with a Large Language Model (Mistral) through ensemble learning. FlexLog also incorporates a cache and retrieval-augmented generation (RAG) to further enhance efficiency and effectiveness. To evaluate FlexLog, we configured four datasets for \task, namely ADFA-U, LOGEVOL-U, SynHDFS-U, and SYNEVOL-U. FlexLog outperforms all baselines by at least 1.2 percentage points (pp) in F1 score while using much less labeled data (62.87 pp reduction). When trained on the same amount of data as the baselines, FlexLog achieves up to a 13 pp increase in F1 score on ADFA-U across varying training dataset sizes. Additionally, FlexLog maintains inference time under one second per log sequence, making it suitable for most applications, except latency-sensitive systems. Further analysis reveals the positive impact of FlexLog's key components: cache, RAG and ensemble learning.

cs.SE↗

arXiv2025

Quantum Machine Learning-based Test Oracle for Autonomous Mobile Robots

Robots are increasingly becoming part of our daily lives, interacting with both the environment and humans to perform their tasks. The software of such robots often undergoes upgrades, for example, to add new functionalities, fix bugs, or delete obsolete functionalities. As a result, regression testing of robot software becomes necessary. However, determining the expected correct behavior of robots (i.e., a test oracle) is challenging due to the potentially unknown environments in which the robots must operate. To address this challenge, machine learning (ML)-based test oracles present a viable solution. This paper reports on the development of a test oracle to support regression testing of autonomous mobile robots built by PAL Robotics (Spain), using quantum machine learning (QML), which enables faster training and the construction of more precise test oracles. Specifically, we propose a hybrid framework, QuReBot, that combines both quantum reservoir computing (QRC) and a simple neural network, inspired by residual connection, to predict the expected behavior of a robot. Results show that QRC alone fails to converge in our case, yielding high prediction error. In contrast, QuReBot converges and achieves 15% reduction of prediction error compared to the classical neural network baseline. Finally, we further examine QuReBot under different configurations and offer practical guidance on optimal settings to support future robot software testing.

cs.SE↗

arXiv2024

Properties of the QCD Matter -- An Experimental Review of Selected Results from RHIC BES Program

In the paper, we discuss the development of the multi-gap resistive plate chamber Time-of-Flight (TOF) technology and the production of the STAR TOF detector in China at the beginning of the 21st century. Then we review recent experimental results from the first beam energy scan program (BES-I) at the Relativistic Heavy Ion Collider (RHIC). Topics cover measurements of collectivity, chirality, criticality, global polarization, strangeness, heavy-flavor, di-lepton and light nuclei productions.

nucl-ex↗

arXiv2024

Pretrain, Prompt, and Transfer: Evolving Digital Twins for Time-to-Event Analysis in Cyber-physical Systems

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 to be conducted, such as anomaly detection and time-to-event analysis (the focus of this paper). Recently, it has been widely accepted that digital Twins (DTs) can serve as an efficient method to aid in the development, maintenance, and safe and secure operation of CPSs. However, CPSs frequently evolve, e.g., with new or updated functionalities, which demand their corresponding DTs be co-evolved, i.e., in synchronization with the CPSs. To that end, we propose a novel method, named PPT, utilizing an uncertainty-aware transfer learning for DT evolution. Specifically, we first pretrain PPT with a pretraining dataset to acquire generic knowledge about the CPSs, followed by adapting it to a specific CPS with the help of prompt tuning. Results highlight that PPT is effective in time-to-event analysis in both elevator and ADSs case studies, on average, outperforming a baseline method by 7.31 and 12.58 in terms of Huber loss, respectively. The experiment results also affirm the effectiveness of transfer learning, prompt tuning and uncertainty quantification in terms of reducing Huber loss by at least 21.32, 3.14 and 4.08, respectively, in both case studies.

cs.SE↗

arXiv2023

PanGu-$π$: Enhancing Language Model Architectures via Nonlinearity Compensation

The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which is definitely proved by a lot of work such as the famous GPT and Llama. However, large models often involve massive computational costs, and practical applications cannot afford such high prices. However, the method of constructing a strong model architecture for LLMs is rarely discussed. We first analyze the state-of-the-art language model architectures and observe the feature collapse problem. Based on the theoretical analysis, we propose that the nonlinearity is also very important for language models, which is usually studied in convolutional neural networks for vision tasks. The series informed activation function is then introduced with tiny calculations that can be ignored, and an augmented shortcut is further used to enhance the model nonlinearity. We then demonstrate that the proposed approach is significantly effective for enhancing the model nonlinearity through carefully designed ablations; thus, we present a new efficient model architecture for establishing modern, namely, PanGu-$π$. Experiments are then conducted using the same dataset and training strategy to compare PanGu-$π$ with state-of-the-art LLMs. The results show that PanGu-$π$-7B can achieve a comparable performance to that of benchmarks with about 10\% inference speed-up, and PanGu-$π$-1B can achieve state-of-the-art performance in terms of accuracy and efficiency. In addition, we have deployed PanGu-$π$-7B in the high-value domains of finance and law, developing an LLM named YunShan for practical application. The results show that YunShan can surpass other models with similar scales on benchmarks.

cs.CL↗

arXiv2023

Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems

Anomaly detection is critical to ensure the security of cyber-physical systems (CPS). However, due to the increasing complexity of attacks and CPS themselves, anomaly detection in CPS is becoming more and more challenging. In our previous work, we proposed a digital twin-based anomaly detection method, called ATTAIN, which takes advantage of both historical and real-time data of CPS. However, such data vary significantly in terms of difficulty. Therefore, similar to human learning processes, deep learning models (e.g., ATTAIN) can benefit from an easy-to-difficult curriculum. To this end, in this paper, we present a novel approach, named digitaL twin-based Anomaly deTecTion wIth Curriculum lEarning (LATTICE), which extends ATTAIN by introducing curriculum learning to optimize its learning paradigm. LATTICE attributes each sample with a difficulty score, before being fed into a training scheduler. The training scheduler samples batches of training data based on these difficulty scores such that learning from easy to difficult data can be performed. To evaluate LATTICE, we use five publicly available datasets collected from five real-world CPS testbeds. We compare LATTICE with ATTAIN and two other state-of-the-art anomaly detectors. Evaluation results show that LATTICE outperforms the three baselines and ATTAIN by 0.906%-2.367% in terms of the F1 score. LATTICE also, on average, reduces the training time of ATTAIN by 4.2% on the five datasets and is on par with the baselines in terms of detection delay time.

cs.LG↗

arXiv2023

Knowledge Distillation-Empowered Digital Twin for Anomaly Detection

Cyber-physical systems (CPSs), like train control and management systems (TCMS), are becoming ubiquitous in critical infrastructures. As safety-critical systems, ensuring their dependability during operation is crucial. Digital twins (DTs) have been increasingly studied for this purpose owing to their capability of runtime monitoring and warning, prediction and detection of anomalies, etc. However, constructing a DT for anomaly detection in TCMS necessitates sufficient training data and extracting both chronological and context features with high quality. Hence, in this paper, we propose a novel method named KDDT for TCMS anomaly detection. KDDT harnesses a language model (LM) and a long short-term memory (LSTM) network to extract contexts and chronological features, respectively. To enrich data volume, KDDT benefits from out-of-domain data with knowledge distillation (KD). We evaluated KDDT with two datasets from our industry partner Alstom and obtained the F1 scores of 0.931 and 0.915, respectively, demonstrating the effectiveness of KDDT. We also explored individual contributions of the DT model, LM, and KD to the overall performance of KDDT, via a comprehensive empirical study, and observed average F1 score improvements of 12.4%, 3%, and 6.05%, respectively.

cs.LG↗

arXiv2023

EvoCLINICAL: Evolving Cyber-Cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System

The Cancer Registry of Norway (CRN) collects information on cancer patients by receiving cancer messages from different medical entities (e.g., medical labs, and hospitals) in Norway. Such messages are validated by an automated cancer registry system: GURI. Its correct operation is crucial since it lays the foundation for cancer research and provides critical cancer-related statistics to its stakeholders. Constructing a cyber-cyber digital twin (CCDT) for GURI can facilitate various experiments and advanced analyses of the operational state of GURI without requiring intensive interactions with the real system. However, GURI constantly evolves due to novel medical diagnostics and treatment, technological advances, etc. Accordingly, CCDT should evolve as well to synchronize with GURI. A key challenge of achieving such synchronization is that evolving CCDT needs abundant data labelled by the new GURI. To tackle this challenge, we propose EvoCLINICAL, which considers the CCDT developed for the previous version of GURI as the pretrained model and fine-tunes it with the dataset labelled by querying a new GURI version. EvoCLINICAL employs a genetic algorithm to select an optimal subset of cancer messages from a candidate dataset and query GURI with it. We evaluate EvoCLINICAL on three evolution processes. The precision, recall, and F1 score are all greater than 91%, demonstrating the effectiveness of EvoCLINICAL. Furthermore, we replace the active learning part of EvoCLINICAL with random selection to study the contribution of transfer learning to the overall performance of EvoCLINICAL. Results show that employing active learning in EvoCLINICAL increases its performances consistently.

cs.LG↗

arXiv2023

Lambda polarization at Electron-ion collider in China

Lambda polarization can be measured through its self-analyzing weak decay, making it an ideal candidate for studying spin effects in high energy scatterings. In lepton-nucleon deeply inelastic scatterings (DIS), Lambda polarization measurements can probe the polarized parton distribution functions (PDFs) and the polarized fragmentation functions (FFs). One of the most promising facilities for high-energy nuclear physics research is the proposed Electron-ion collider in China (EicC). As a next-generation facility, EicC is set to propel our understandings of nuclear physics to new heights. In this article, we study the Lambda production in electron-proton collision at EicC energy, in particular Lambda's reconstruction based on the performance of the designed EicC detector. In addition, taking spontaneous transverse polarization as an example, we provide a theoretical prediction with statistical projection based on one month of EicC data taking, offering valuable insights into future research prospects.

nucl-ex↗