Context: Software Quality Assurance (SQA) is a fundamental part of software engineering to ensure stakeholders that software products work as expected after release in operation. Machine Learning (ML) has proven to be able to boost SQA activities and contribute to the development of quality software systems. In this context, Causal Reasoning is gaining increasing interest as a methodology to go beyond a purely data-driven approach by exploiting the use of causality for more effective SQA strategies. Objective: Provide a broad and detailed overview of the use of causal reasoning for SQA activities, in order to support researchers to access this research field, identifying room for application, main challenges and research opportunities. Methods: A systematic review of the scientific literature on causal reasoning for SQA. The study has found, classified, and analyzed 86 articles, according to established guidelines for software engineering secondary studies. Results: Results highlight the primary areas within SQA where causal reasoning has been applied, the predominant methodologies used, and the level of maturity of the proposed solutions. Fault localization is the activity where causal reasoning is more exploited, especially in the web services/microservices domain, but other tasks like testing are rapidly gaining popularity. Both causal inference and causal discovery are exploited, with the Pearl's graphical formulation of causality being preferred, likely due to its intuitiveness. Tools to favour their application are appearing at a fast pace - most of them after 2021. Conclusions: The findings show that causal reasoning is a valuable means for SQA tasks with respect to multiple quality attributes, especially during V&V, evolution and maintenance to ensure reliability, while it is not yet fully exploited for phases like ...
The rapid growth in the use of Large Language Models (LLMs) and AI Agents as part of software development and deployment is revolutionizing the information technology landscape. While code generation receives significant attention, a higher-impact application lies in using AI agents for operational resilience of cloud services, which currently require significant human effort and domain knowledge. There is a growing interest in AI for IT Operations (AIOps) which aims to automate complex operational tasks, like fault localization and root cause analysis, thereby reducing human intervention and customer impact. However, achieving the vision of autonomous and self-healing clouds through AIOps is hampered by the lack of standardized frameworks for building, evaluating, and improving AIOps agents. This vision paper lays the groundwork for such a framework by first framing the requirements and then discussing design decisions that satisfy them. We also propose AIOpsLab, a prototype implementation leveraging agent-cloud-interface that orchestrates an application, injects real-time faults using chaos engineering, and interfaces with an agent to localize and resolve the faults. We report promising results and lay the groundwork to build a modular and robust framework for building, evaluating, and improving agents for autonomous clouds.
Debugging is one of the most time-consuming and expensive tasks in software development. Several formula-based fault localization (FBFL) methods have been proposed, but they fail to guarantee a set of diagnoses across all failing tests or may produce redundant diagnoses that are not subset-minimal, particularly for programs with multiple faults. This paper introduces a novel fault localization approach for C programs with multiple faults. CFaults leverages Model-Based Diagnosis (MBD) with multiple observations and aggregates all failing test cases into a unified MaxSAT formula. Consequently, our method guarantees consistency across observations and simplifies the fault localization procedure. Experimental results on two benchmark sets of C programs, TCAS and C-Pack-IPAs, show that CFaults is faster than other FBFL approaches like BugAssist and SNIPER. Moreover, CFaults only generates subset-minimal diagnoses of faulty statements, whereas the other approaches tend to enumerate redundant diagnoses.
Runtime failure and performance degradation is commonplace in modern cloud systems. For cloud providers, automatically determining the root cause of incidents is paramount to ensuring high reliability and availability as prompt fault localization can enable faster diagnosis and triage for timely resolution. A compelling solution explored in recent work is causal reasoning using causal graphs to capture relationships between varied cloud system performance metrics. To be effective, however, systems developers must correctly define the causal graph of their system, which is a time-consuming, brittle, and challenging task that increases in difficulty for large and dynamic systems and requires domain expertise. Alternatively, automated data-driven approaches have limited efficacy for cloud systems due to the inherent rarity of incidents. In this work, we present Atlas, a novel approach to automatically synthesizing causal graphs for cloud systems. Atlas leverages large language models (LLMs) to generate causal graphs using system documentation, telemetry, and deployment feedback. Atlas is complementary to data-driven causal discovery techniques, and we further enhance Atlas with a data-driven validation step. We evaluate Atlas across a range of fault localization scenarios and demonstrate that Atlas is capable of generating causal graphs in a scalable and generalizable manner, with performance that far surpasses that of data-driven algorithms and is commensurate to the ground-truth baseline.
The newly deployed service -- one kind of change service, could lead to a new type of minority fault. Existing state-of-the-art methods for fault localization rarely consider the imbalanced fault classification in change service. This paper proposes a novel method that utilizes decision rule sets to deal with highly imbalanced data by optimizing the F1 score subject to cardinality constraints. The proposed method greedily generates the rule with maximal marginal gain and uses an efficient minorize-maximization (MM) approach to select rules iteratively, maximizing a non-monotone submodular lower bound. Compared with existing fault localization algorithms, our algorithm can adapt to the imbalanced fault scenario of change service, and provide interpretable fault causes which are easy to understand and verify. Our method can also be deployed in the online training setting, with only about 15% training overhead compared to the current SOTA methods. Empirical studies showcase that our algorithm outperforms existing fault localization algorithms in both accuracy and model interpretability.
Due to the scarcity of fault samples and the complexity of non-linear and non-smooth characteristics data in hydroelectric units, most of the traditional hydroelectric unit fault localization methods are difficult to carry out accurate localization. To address these problems, a sparse autoencoder (SAE)-generative adversarial network (GAN)-wavelet noise reduction (WNR)- manifold-boosted deep learning (SG-WMBDL) based fault localization method for hydroelectric units is proposed. To overcome the data scarcity, a SAE is embedded into the GAN to generate more high-quality samples in the data generation module. Considering the signals involving non-linear and non-smooth characteristics, the improved WNR which combining both soft and hard thresholding and local linear embedding (LLE) are utilized to the data preprocessing module in order to reduce the noise and effectively capture the local features. In addition, to seek higher performance, the novel Adaptive Boost (AdaBoost) combined with multi deep learning is proposed to achieve accurate fault localization. The experimental results show that the SG-WMBDL can locate faults for hydroelectric units under a small number of fault samples with non-linear and non-smooth characteristics on higher precision and accuracy compared to other frontier methods, which verifies the effectiveness and practicality of the proposed method.
Structural decoupling has played an essential role in model-based fault isolation and estimation in past decades, which facilitates accurate fault localization and reconstruction thanks to the diagonal transfer matrix design. However, traditional methods exhibit limited effectiveness in modeling high-dimensional nonlinearity and big data, and the decoupling idea has not been well-valued in data-driven frameworks. Known for big data and complex feature extraction capabilities, deep learning has recently been used to develop residual generation models. Nevertheless, it lacks decoupling-related diagnostic designs. To this end, this paper proposes a transfer learning-based input-output decoupled network (TDN) for diagnostic purposes, which consists of an input-output decoupled network (IDN) and a pre-trained variational autocoder (VAE). In IDN, uncorrelated residual variables are generated by diagonalization and parallel computing operations. During the transfer learning phase, knowledge of normal status is provided according to VAE's loss and maximum mean discrepancy loss to guide the training of IDN. After training, IDN learns the mapping from faulty to normal, thereby serving as the fault detection index and the estimated fault signal simultaneously. At last, the effectiveness of the developed TDN is verified by a numerical example and a chemical simulation.
Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of current infilling-style methods, which impedes LLMs from fully leveraging pre-trained knowledge for program repair. In addition, while some LLMs can locate and repair bugs in certain functions using the related artifacts (e.g., test cases), existing methods still depend on statement-level fault localization methods to provide a list of buggy hunks for repair. This restriction hinders LLMs from exploring potential patches beyond the given locations. In this paper, we investigate a new approach to adapt LLMs to program repair. Our core insight is that LLM's APR capability can be greatly improved by simply aligning the output to their training objective and allowing them to refine the whole program without first identifying faulty statements. Based on this insight, we designed D4C, a straightforward prompting framework for APR. D4C can repair 180 bugs correctly in Defects4J, with each patch being sampled only 10 times. This surpasses the SOTA APR methods with perfect fault localization by 10% and reduces the patch sampling number by 90%. Our findings reveal that (1) objective alignment is crucial for fully exploiting LLM's pre-trained capability, and (2) replacing the traditional localize-buggy-hunks-then-repair workflow with direct debugging is more effective for LLM-based APR methods. Thus, we believe this paper introduces a new mindset for harnessing LLMs in APR.
Prompting has become one of the main approaches to leverage emergent capabilities of Large Language Models [Brown et al. NeurIPS 2020, Wei et al. TMLR 2022, Wei et al. NeurIPS 2022]. Recently, researchers and practitioners have been "playing" with prompts (e.g., In-Context Learning) to see how to make the most of pre-trained Language Models. By homogeneously dissecting more than a hundred articles, we investigate how software testing and verification research communities have leveraged LLMs capabilities. First, we validate that downstream tasks are adequate to convey a nontrivial modular blueprint of prompt-based proposals in scope. Moreover, we name and classify the concrete downstream tasks we recover in both validation research papers and solution proposals. In order to perform classification, mapping, and analysis, we also develop a novel downstream-task taxonomy. The main taxonomy requirement is to highlight commonalities while exhibiting variation points of task types that enable pinpointing emerging patterns in a varied spectrum of Software Engineering problems that encompasses testing, fuzzing, fault localization, vulnerability detection, static analysis, and program verification approaches. Avenues for future research are also discussed based on conceptual clusters induced by the taxonomy.
Researchers have made significant progress in automating the software development process in the past decades. Recent progress in Large Language Models (LLMs) has significantly impacted the development process, where developers can use LLM-based programming assistants to achieve automated coding. Nevertheless, software engineering involves the process of program improvement apart from coding, specifically to enable software maintenance (e.g. bug fixing) and software evolution (e.g. feature additions). In this paper, we propose an automated approach for solving GitHub issues to autonomously achieve program improvement. In our approach called AutoCodeRover, LLMs are combined with sophisticated code search capabilities, ultimately leading to a program modification or patch. In contrast to recent LLM agent approaches from AI researchers and practitioners, our outlook is more software engineering oriented. We work on a program representation (abstract syntax tree) as opposed to viewing a software project as a mere collection of files. Our code search exploits the program structure in the form of classes/methods to enhance LLM's understanding of the issue's root cause, and effectively retrieve a context via iterative search. The use of spectrum-based fault localization using tests, further sharpens the context, as long as a test-suite is available. Experiments on SWE-bench-lite (300 real-life GitHub issues) show increased efficacy in solving GitHub issues (19% on SWE-bench-lite), which is higher than the efficacy of the recently reported SWE-agent. In addition, AutoCodeRover achieved this efficacy with significantly lower cost (on average, $0.43 USD), compared to other baselines. We posit that our workflow enables autonomous software engineering, where, in future, auto-generated code from LLMs can be autonomously improved.
Ever since Large Language Models (LLMs) and related applications have become broadly available, several studies investigated their potential for assisting educators and supporting students in higher education. LLMs such as Codex, GPT-3.5, and GPT 4 have shown promising results in the context of large programming courses, where students can benefit from feedback and hints if provided timely and at scale. This paper explores the quality of GPT-4 Turbo's generated output for prompts containing both the programming task specification and a student's submission as input. Two assignments from an introductory programming course were selected, and GPT-4 was asked to generate feedback for 55 randomly chosen, authentic student programming submissions. The output was qualitatively analyzed regarding correctness, personalization, fault localization, and other features identified in the material. Compared to prior work and analyses of GPT-3.5, GPT-4 Turbo shows notable improvements. For example, the output is more structured and consistent. GPT-4 Turbo can also accurately identify invalid casing in student programs' output. In some cases, the feedback also includes the output of the student program. At the same time, inconsistent feedback was noted such as stating that the submission is correct but an error needs to be fixed. The present work increases our understanding of LLMs' potential, limitations, and how to integrate them into e-assessment systems, pedagogical scenarios, and instructing students who are using applications based on GPT-4.
The recent increase in renewable energy penetration at the distribution level introduces a multi-directional power flow that outdated traditional fault location techniques. To this extent, the development of new methods is needed to ensure fast and accurate fault localization and, hence, strengthen power system reliability. This paper proposes a data-driven ground fault location method for the power distribution system. An 11-bus 20 kV power system is modeled in Matlab/Simulink to simulate ground faults. The faults are generated at different locations and under various system operational states. Time-domain faulted three-phase voltages at the system substation are then analyzed with discrete wavelet transform. Statistical quantities of the processed data are eventually used to train an Artificial Neural Network (ANN) to find a mapping between computed voltage features and faults. Specifically, three ANNs allow the prediction of faulted phase, faulted branch, and fault distance from the system substation separately. According to the results, the method shows good potential, with a total relative error of 0,4% for fault distance prediction. The method is applied to datasets with unknown system states to test robustness.
Fault localization is challenging in online micro-service due to the wide variety of monitoring data volume, types, events and complex interdependencies in service and components. Faults events in services are propagative and can trigger a cascade of alerts in a short period of time. In the industry, fault localization is typically conducted manually by experienced personnel. This reliance on experience is unreliable and lacks automation. Different modules present information barriers during manual localization, making it difficult to quickly align during urgent faults. This inefficiency lags stability assurance to minimize fault detection and repair time. Though actionable methods aimed to automatic the process, the accuracy and efficiency are less than satisfactory. The precision of fault localization results is of paramount importance as it underpins engineers trust in the diagnostic conclusions, which are derived from multiple perspectives and offer comprehensive insights. Therefore, a more reliable method is required to automatically identify the associative relationships among fault events and propagation path. To achieve this, KGroot uses event knowledge and the correlation between events to perform root cause reasoning by integrating knowledge graphs and GCNs for RCA. FEKG is built based on historical data, an online graph is constructed in real-time when a failure event occurs, and the similarity between each knowledge graph and online graph is compared using GCNs to pinpoint the fault type through a ranking strategy. Comprehensive experiments demonstrate KGroot can locate the root cause with accuracy of 93.5% top 3 potential causes in second-level. This performance matches the level of real-time fault diagnosis in the industrial environment and significantly surpasses state-of-the-art baselines in RCA in terms of effectiveness and efficiency.
The widespread availability of Large Language Models (LLMs) within Integrated Development Environments (IDEs) has led to their speedy adoption. Conversational interactions with LLMs enable programmers to obtain natural language explanations for various software development tasks. However, LLMs often leap to action without sufficient context, giving rise to implicit assumptions and inaccurate responses. Conversations between developers and LLMs are primarily structured as question-answer pairs, where the developer is responsible for asking the the right questions and sustaining conversations across multiple turns. In this paper, we draw inspiration from interaction patterns and conversation analysis -- to design Robin, an enhanced conversational AI-assistant for debugging. Through a within-subjects user study with 12 industry professionals, we find that equipping the LLM to -- (1) leverage the insert expansion interaction pattern, (2) facilitate turn-taking, and (3) utilize debugging workflows -- leads to lowered conversation barriers, effective fault localization, and 5x improvement in bug resolution rates.
Converting deep learning models between frameworks is a common step to maximize model compatibility across devices and leverage optimization features that may be exclusively provided in one deep learning framework. However, this conversion process may be riddled with bugs, making the converted models either undeployable or problematic, considerably degrading their prediction correctness. In this paper, we propose an automated approach for fault localization and repair, FetaFix, during model conversion between deep learning frameworks. FetaFix is capable of detecting and fixing faults introduced in model input, parameters, hyperparameters, and the model graph during conversion. FetaFix uses a set of fault types (mined from surveying common conversion issues reported in code repositories and forums) to localize potential conversion faults in the converted target model and then repair them appropriately, e.g., replacing the parameters of the target model with those from the source model. This is done iteratively for every image in the dataset, comparing output label differences between the source model and the converted target model until all differences are resolved. We evaluate the effectiveness of FetaFix in fixing model conversion bugs of three widely used image recognition models converted across four different deep learning frameworks. Overall, FetaFix was able to fix $462$ out of $755$ detected conversion faults, either completely repairing or significantly improving the performance of $14$ out of the $15$ erroneous conversion cases.
In Federated Learning, clients train models on local data and send updates to a central server, which aggregates them into a global model using a fusion algorithm. This collaborative yet privacy-preserving training comes at a cost. FL developers face significant challenges in attributing global model predictions to specific clients. Localizing responsible clients is a crucial step towards (a) excluding clients primarily responsible for incorrect predictions and (b) encouraging clients who contributed high-quality models to continue participating in the future. Existing ML debugging approaches are inherently inapplicable as they are designed for single-model, centralized training. We introduce TraceFL, a fine-grained neuron provenance capturing mechanism that identifies clients responsible for a global model's prediction by tracking the flow of information from individual clients to the global model. Since inference on different inputs activates a different set of neurons of the global model, TraceFL dynamically quantifies the significance of the global model's neurons in a given prediction, identifying the most crucial neurons in the global model. It then maps them to the corresponding neurons in every participating client to determine each client's contribution, ultimately localizing the responsible client. We evaluate TraceFL on six datasets, including two real-world medical imaging datasets and four neural networks, including advanced models such as GPT. TraceFL achieves 99% accuracy in localizing the responsible client in FL tasks spanning both image and text classification tasks. At a time when state-of-the-artML debugging approaches are mostly domain-specific (e.g., image classification only), TraceFL is the first technique to enable highly accurate automated reasoning across a wide range of FL applications.
Systolic arrays are a prominent choice for deep neural network (DNN) accelerators because they offer parallelism and efficient data reuse. Improving the reliability of DNN accelerators is crucial as hardware faults can degrade the accuracy of DNN inferencing. Systolic arrays make use of a large number of processing elements (PEs) for parallel processing, but when one PE is faulty, the error propagates and affects the outcomes of downstream PEs. Due to the large number of PEs, the cost associated with implementing hardware-based runtime monitoring of every single PE is infeasible. We present a solution to optimize the placement of hardware monitors within systolic arrays. We first prove that $2N-1$ monitors are needed to localize a single faulty PE and we also derive the monitor placement. We show that a second placement optimization problem, which minimizes the set of candidate faulty PEs for a given number of monitors, is NP-hard. Therefore, we propose a heuristic approach to balance the reliability and hardware resource utilization in DNN accelerators when number of monitors is limited. Experimental evaluation shows that to localize a single faulty PE, an area overhead of only 0.33% is incurred for a $256\times 256$ systolic array.
Accurate and quick identification of high-impedance faults is critical for the reliable operation of distribution systems. Unlike other faults in power grids, HIFs are very difficult to detect by conventional overcurrent relays due to the low fault current. Although HIFs can be affected by various factors, the voltage current characteristics can substantially imply how the system responds to the disturbance and thus provides opportunities to effectively localize HIFs. In this work, we propose a data-driven approach for the identification of HIF events. To tackle the nonlinearity of the voltage current trajectory, first, we formulate optimization problems to approximate the trajectory with piecewise functions. Then we collect the function features of all segments as inputs and use the support vector machine approach to efficiently identify HIFs at different locations. Numerical studies on the IEEE 123-node test feeder demonstrate the validity and accuracy of the proposed approach for real-time HIF identification.
Policies trained via reinforcement learning (RL) are often very complex even for simple tasks. In an episode with n time steps, a policy will make n decisions on actions to take, many of which may appear non-intuitive to the observer. Moreover, it is not clear which of these decisions directly contribute towards achieving the reward and how significant their contribution is. Given a trained policy, we propose a black-box method based on statistical covariance estimation that clusters the states of the environment and ranks each cluster according to the importance of decisions made in its states. We compare our measure against a previous statistical fault localization based ranking procedure.
Timely formative feedback is considered as one of the most important drivers for effective learning. Delivering timely and individualized feedback is particularly challenging in large classes in higher education. Recently Large Language Models such as GPT-3 became available to the public that showed promising results on various tasks such as code generation and code explanation. This paper investigates the potential of AI in providing personalized code correction and generating feedback. Based on existing student submissions of two different real-world assignments, the correctness of the AI-aided e-assessment as well as the characteristics such as fault localization, correctness of hints, and code style suggestions of the generated feedback are investigated. The results show that 73 % of the submissions were correctly identified as either correct or incorrect. In 59 % of these cases, GPT-3.5 also successfully generated effective and high-quality feedback. Additionally, GPT-3.5 exhibited weaknesses in its evaluation, including localization of errors that were not the actual errors, or even hallucinated errors. Implications and potential new usage scenarios are discussed.