Jinfu Chen

Huashan Chen, Zhenyu Qi, Haotang Li et al.

Large Language Models (LLMs) have become central to automated code generation, yet existing approaches operate within a single-LLM paradigm: one model is selected and applied throughout the entire generation process. We observe that different LLMs exhibit complementary strengths: no single model dominates across all programming languages, algorithmic problem categories, or development stages. Multi-LLM collaboration, structured as per-stage, per-category routing rather than majority voting, produces higher-quality code than any individual model. Based on this observation, we propose PerfOrch, a multi-agent orchestration system that decomposes code generation into four collaborative agents: categorization, generation, debugging, and refinement. Each agent maintains a Memory module: a ranking matrix indexed by programming language and problem category, constructed from offline profiling and consulted at runtime to select the most suitable model for each task. We evaluate PerfOrch on two benchmarks, HumanEval-X and EffiBench-X, totaling 2,500 problems across five languages (Python, Java, C++, Go, and Rust). PerfOrch achieves average pass@1 rates of 97.19% on HumanEval-X and 95.83% on EffiBench-X, improving over the strongest single-model pipeline by 1.22-14.58 percentage points across languages. Notably, Memory rankings constructed solely from HumanEval-X profiling generalize to the entirely unseen EffiBench-X benchmark without re-profiling, demonstrating that the complementary-strength patterns PerfOrch exploits are properties of the models rather than artifacts of a specific problem distribution. Beyond correctness, PerfOrch improves execution time for 61-90% of solved problems with mean speedups of 4.7-29.9%, matching the refinement coverage of exhaustive multi-model evaluation at roughly half the token cost.

Bilal Ahmad, Jinfu Chen, Haibao Chen

Heart disease remains one of the leading causes of morbidity and mortality worldwide, necessitating the development of effective diagnostic tools to enable early diagnosis and clinical decision-making. This study evaluates the impact of feature selection techniques Mutual Information (MI), Analysis of Variance (ANOVA), and Chi-Square on the predictive performance of various machine learning (ML) and deep learning (DL) models using a dataset of clinical indicators for heart disease. Eleven ML/DL models were assessed using metrics such as precision, recall, AUC score, F1-score, and accuracy. Results indicate that MI outperformed other methods, particularly for advanced models like neural networks, achieving the highest accuracy of 82.3% and recall score of 0.94. Logistic regression (accuracy 82.1%) and random forest (accuracy 80.99%) also demonstrated improved performance with MI. Simpler models such as Naive Bayes and decision trees achieved comparable results with ANOVA and Chi-Square, yielding accuracies of 76.45% and 75.99%, respectively, making them computationally efficient alternatives. Conversely, k Nearest Neighbors (KNN) and Support Vector Machines (SVM) exhibited lower performance, with accuracies ranging between 51.52% and 54.43%, regardless of the feature selection method. This study provides a comprehensive comparison of feature selection methods for heart disease prediction, demonstrating the critical role of feature selection in optimizing model performance. The results offer practical guidance for selecting appropriate feature selection techniques based on the chosen classification algorithm, contributing to the development of more accurate and efficient diagnostic tools for enhanced clinical decision-making in cardiology.

Rubing Huang, Weifeng Sun, Tsong Yueh Chen et al.

Failure region, where failure-causing inputs reside, has provided many insights to enhance testing effectiveness of many testing methods. Failure region may also provide some important information to support other processes such as software debugging. When a testing method detects a software failure, indicating that a failure-causing input is identified, the next important question is about how to identify the failure region based on this failure-causing input, i.e., Identification of Failure Regions (IFR). In this paper, we introduce a new IFR strategy, namely Search for Boundary (SB), to identify an approximate failure region of a numeric input domain. SB attempts to identify additional failure-causing inputs that are as close to the boundary of the failure region as possible. To support SB, we provide a basic procedure, and then propose two methods, namely Fixed-orientation Search for Boundary (FSB) and Diverse-orientation Search for Boundary (DSB). In addition, we implemented an automated experimentation platform to integrate these methods. In the experiments, we evaluated the proposed SB methods using a series of simulation studies andempirical studies with different types of failure regions. The results show that our methods can effectively identify a failure region, within the limited testing resources.

Rubing Huang, Quanjun Zhang, Dave Towey et al.

Regression test case prioritization (RTCP) aims to improve the rate of fault detection by executing more important test cases as early as possible. Various RTCP techniques have been proposed based on different coverage criteria. Among them, a majority of techniques leverage code coverage information to guide the prioritization process, with code units being considered individually, and in isolation. In this paper, we propose a new coverage criterion, code combinations coverage, that combines the concepts of code coverage and combination coverage. We apply this coverage criterion to RTCP, as a new prioritization technique, code combinations coverage based prioritization (CCCP). We report on empirical studies conducted to compare the testing effectiveness and efficiency of CCCP with four popular RTCP techniques: total, additional, adaptive random, and search-based test prioritization. The experimental results show that even when the lowest combination strength is assigned, overall, the CCCP fault detection rates are greater than those of the other four prioritization techniques. The CCCP prioritization costs are also found to be comparable to the additional test prioritization technique. Moreover, our results also show that when the combination strength is increased, CCCP provides higher fault detection rates than the state-of-the-art, regardless of the levels of code coverage.

Jinfu Chen, Hilary Ackah-Arthur, Chengying Mao et al.

Random testing (RT) is a black-box software testing technique that tests programs by generating random test inputs. It is a widely used technique for software quality assurance, but there has been much debate by practitioners concerning its failure-detection effectiveness. RT is argued to be possibly less effective by some researchers as it does not utilize any information about the program under test. Efforts to mainly improve the failure-detection capability of RT, have led to the proposition of Adaptive Random Testing (ART). ART takes advantage of the location information of previous non-fault-detecting test cases to enhance effectiveness as compared to RT. The approach has gained popularity and has a large number of theoretical studies and methods that employ different notions. In this review, our goal is to provide an overview of existing ART studies. We classify all ART studies and assess existing ART methods for numeric programs with a focus on their motivation, strategy, and findings. The study also discusses several worthy avenues related to ART. The review uses 109 ART papers in several journals, workshops, and conference proceedings. The results of the review show that significant research efforts have been made towards the field of ART, however further empirical studies are still required to make the technique applicable in different test scenarios in order to impact on the industry.