arXiv subjects

Gabin An

Publications and source records attributed to Gabin An.

15 recordsLinked to original sources

arXiv2026

Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops

Iterative repair loops have become a core design pattern in LLM-based software engineering systems. These workflows repeatedly generate, validate, and repair artifacts using feedback such as compiler errors or test failures. Despite their widespread use, the impact of repair-loop iteration limits remains poorly understood, as most prior work adopts fixed, often arbitrary, repair budgets. We study repair-loop effectiveness across multiple software engineering tasks, including code generation, test generation, and code translation. Across several representative workflows, datasets, and contemporary low-cost LLMs, we observe a consistent pattern of diminishing returns: the first three to four repair iterations account for most achievable gains, while later iterations contribute only marginal improvements. We further find that repair behavior is influenced more strongly by workflow orchestration and feedback design than by the underlying model itself. These results suggest that repair budgets should be treated as an explicit experimental variable, as they directly affect evaluation outcomes, computational cost, runtime, and reproducibility in LLM-based software engineering research.

cs.SE↗

arXiv2025

Finding the Needle in the Crash Stack: Industrial-Scale Crash Root Cause Localization with AutoCrashFL

Fault Localization (FL) aims to identify root causes of program failures. FL typically targets failures observed from test executions, and as such, often involves dynamic analyses to improve accuracy, such as coverage profiling or mutation testing. However, for large industrial software, measuring coverage for every execution is prohibitively expensive, making the use of such techniques difficult. To address these issues and apply FL in an industrial setting, this paper proposes AutoCrashFL, an LLM agent for the localization of crashes that only requires the crashdump from the Program Under Test (PUT) and access to the repository of the corresponding source code. We evaluate AutoCrashFL against real-world crashes of SAP HANA, an industrial software project consisting of more than 35 million lines of code. Experiments reveal that AutoCrashFL is more effective in localization, as it identified 30% crashes at the top, compared to 17% achieved by the baseline. Through thorough analysis, we find that AutoCrashFL has attractive practical properties: it is relatively more effective for complex bugs, and it can indicate confidence in its results. Overall, these results show the practicality of LLM agent deployment on an industrial scale.

cs.SE↗

arXiv2025

Identifying Bug Inducing Commits by Combining Fault Localisation and Code Change Histories

A Bug Inducing Commit (BIC) is a code change that introduces a bug into the codebase. Although the abnormal or unexpected behavior caused by the bug may not manifest immediately, it will eventually lead to program failures further down the line. When such a program failure is observed, identifying the relevant BIC can aid in the bug resolution process, because knowing the original intent and context behind the code change, as well as having a link to the author of that change, can facilitate bug triaging and debugging. However, existing BIC identification techniques have limitations. Bisection can be computationally expensive because it requires executing failing tests against previous versions of the codebase. Other techniques rely on the availability of specific post hoc artifacts, such as bug reports or bug fixes. In this paper, we propose a technique called Fonte that aims to identify the BIC with a core concept that a commit is more likely to be a BIC if it has more recently modified code elements that are highly suspicious of containing the bug. To realise this idea, Fonte leverages two fundamental relationships in software: the failure-to-code relationship, which can be quantified through fault localisation techniques, and the code-to-commit relationship, which can be obtained from version control systems. Our empirical evaluation using 206 real-world BICs from open-source Java projects shows that Fonte significantly outperforms state-of-the-art BIC identification techniques, achieving up to 45.8% higher MRR. We also report that the ranking scores produced by Fonte can be used to perform weighted bisection. Finally, we apply Fonte to a large-scale industry project with over 10M lines of code, and show that it can rank the actual BIC within the top five commits for 87% of the studied real batch-testing failures, and save the BIC inspection cost by 32% on average.

cs.SE↗

arXiv2025

METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries

Code documentation can, if written precisely, help developers better understand the code they accompany. However, unlike code, code documentation cannot be automatically verified via execution, potentially leading to inconsistencies between documentation and the actual behavior. While such inconsistencies can be harmful for the developer's understanding of the code, checking and finding them remains a costly task due to the involvement of human engineers. This paper proposes METAMON, which uses an existing search-based test generation technique to capture the current program behavior in the form of test cases, and subsequently uses LLM-based code reasoning to identify the generated regression test oracles that are not consistent with the program specifications in the documentation. METAMON is supported in this task by metamorphic testing and self-consistency. An empirical evaluation against 9,482 pairs of code documentation and code snippets, generated using five open-source projects from Defects4J v2.0.1, shows that METAMON can classify the code-and-documentation inconsistencies with a precision of 0.72 and a recall of 0.48.

cs.SE↗

arXiv2025

COSMosFL: Ensemble of Small Language Models for Fault Localisation

LLMs are rapidly being adopted to build powerful tools and agents for software engineering, but most of them rely heavily on extremely large closed-source models. This, in turn, can hinder wider adoption due to security issues as well as financial cost and environmental impact. Recently, a number of open source Small Language Models (SLMs) are being released and gaining traction. While SLMs are smaller, more energy-efficient, and therefore easier to locally deploy, they tend to show worse performance when compared to larger closed LLMs. We present COSMos, a task-level LLM ensemble technique that uses voting mechanism, to provide a broader range of choice between SLMs and LLMs. We instantiate COSMos with an LLM-based Fault Localisation technique, AutoFL, and report the cost-benefit trade-off between LLM accuracy and various costs such as energy consumption, inference time, and the number of tokens used. An empirical evaluation using Defects4J shows that COSMos can build effective ensembles that can achieve Pareto-optimality in terms of FL accuracy and inference cost, when compared to individual models.

cs.SE↗

arXiv2024

Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths

Large Language Models are increasingly used to build agents to perform more complex tasks. As LLMs perform more complicated reasoning through longer interactions, self-consistency, i.e., the idea that the answer obtained from sampling and marginalising a number of multiple independent inferences is more likely to be correct, has received much attention as a simple validation technique. This paper aims to empirically verify this intuitive hypothesis by predicting the correctness of answers obtained using self-consistency from properties of the samples of reasoning paths. We introduce Lachesis, a predictive model for self-consistency based LLM inferences, and empirically evaluate it using AutoFL, a recently proposed LLM-based fault localisation technique, as the target technique that uses self-consistency. Lachesis converts collected reasoning paths from AutoFL using specifically designed reasoning path representations, and trains LSTM and GCN models to predict whether a given set of reasoning paths would result in a correct answer. The results suggest that Lachesis can predict the correctness of answers with a precision of up to 0.8136, highlighting the possibility of training a predictive model that can allow early termination of inferences that are not likely to be successful.

cs.SE↗

arXiv2023

Just-in-Time Flaky Test Detection via Abstracted Failure Symptom Matching

We report our experience of using failure symptoms, such as error messages or stack traces, to identify flaky test failures in a Continuous Integration (CI) pipeline for a large industrial software system, SAP HANA. Although failure symptoms are commonly used to identify similar failures, they have not previously been employed to detect flaky test failures. Our hypothesis is that flaky failures will exhibit symptoms distinct from those of non-flaky failures. Consequently, we can identify recurring flaky failures, without rerunning the tests, by matching the failure symptoms to those of historical flaky runs. This can significantly reduce the need for test reruns, ultimately resulting in faster delivery of test results to developers. To facilitate the process of matching flaky failures across different execution instances, we abstract newer test failure symptoms before matching them to the known patterns of flaky failures, inspired by previous research in the fields of failure deduplication and log analysis. We evaluate our symptom-based flakiness detection method using actual failure symptoms gathered from CI data of SAP HANA during a six-month period. Our method shows the potential of using failure symptoms to identify recurring flaky failures, achieving a precision of at least 96%, while saving approximately 58% of the machine time compared to the traditional rerun strategy. Analysis of the false positives and the feedback from developers underscore the importance of having descriptive and informative failure symptoms for both the effective deployment of this symptom-based approach and the debugging of flaky tests.

cs.SE↗

arXiv2023

A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization

Fault Localization (FL), in which a developer seeks to identify which part of the code is malfunctioning and needs to be fixed, is a recurring challenge in debugging. To reduce developer burden, many automated FL techniques have been proposed. However, prior work has noted that existing techniques fail to provide rationales for the suggested locations, hindering developer adoption of these techniques. With this in mind, we propose AutoFL, a Large Language Model (LLM)-based FL technique that generates an explanation of the bug along with a suggested fault location. AutoFL prompts an LLM to use function calls to navigate a repository, so that it can effectively localize faults over a large software repository and overcome the limit of the LLM context length. Extensive experiments on 798 real-world bugs in Java and Python reveal AutoFL improves method-level acc@1 by up to 233.3% over baselines. Furthermore, developers were interviewed on their impression of AutoFL-generated explanations, showing that developers generally liked the natural language explanations of AutoFL, and that they preferred reading a few, high-quality explanations instead of many.

cs.SE↗

arXiv2023

Learning Test-Mutant Relationship for Accurate Fault Localisation

Context: Automated fault localisation aims to assist developers in the task of identifying the root cause of the fault by narrowing down the space of likely fault locations. Simulating variants of the faulty program called mutants, several Mutation Based Fault Localisation (MBFL) techniques have been proposed to automatically locate faults. Despite their success, existing MBFL techniques suffer from the cost of performing mutation analysis after the fault is observed. Method: To overcome this shortcoming, we propose a new MBFL technique named SIMFL (Statistical Inference for Mutation-based Fault Localisation). SIMFL localises faults based on the past results of mutation analysis that has been done on the earlier version in the project history, allowing developers to make predictions on the location of incoming faults in a just-in-time manner. Using several statistical inference methods, SIMFL models the relationship between test results of the mutants and their locations, and subsequently infers the location of the current faults. Results: The empirical study on Defects4J dataset shows that SIMFL can localise 113 faults on the first rank out of 224 faults, outperforming other MBFL techniques. Even when SIMFL is trained on the predicted kill matrix, SIMFL can still localise 95 faults on the first rank out of 194 faults. Moreover, removing redundant mutants significantly improves the localisation accuracy of SIMFL by the number of faults localised at the first rank up to 51. Conclusion: This paper proposes a new MBFL technique called SIMFL, which exploits ahead-of-time mutation analysis to localise current faults. SIMFL is not only cost-effective, as it does not need a mutation analysis after the fault is observed, but also capable of localising faults accurately.

cs.SE↗

arXiv2022

Fonte: Finding Bug Inducing Commits from Failures

A Bug Inducing Commit (BIC) is a commit that introduces a software bug into the codebase. Knowing the relevant BIC for a given bug can provide valuable information for debugging as well as bug triaging. However, existing BIC identification techniques are either too expensive (because they require the failing tests to be executed against previous versions for bisection) or inapplicable at the debugging time (because they require post hoc artefacts such as bug reports or bug fixes). We propose Fonte, an efficient and accurate BIC identification technique that only requires test coverage. Fonte combines Fault Localisation (FL) with BIC identification and ranks commits based on the suspiciousness of the code elements that they modified. Fonte reduces the search space of BICs using failure coverage as well as a filter that detects commits that are merely style changes. Our empirical evaluation using 130 real-world BICs shows that Fonte significantly outperforms state-of-the-art BIC identification techniques based on Information Retrieval as well as neural code embedding models, achieving at least 39% higher MRR. We also report that the ranking scores produced by Fonte can be used to perform weighted bisection, further reducing the cost of BIC identification. Finally, we apply Fonte to a large-scale industry project with over 10M lines of code, and show that it can rank the actual BIC within the top five commits for 87% of the studied real batch-testing failures, and save the BIC inspection cost by 32% on average.

cs.SE↗

arXiv2021

Searching for Multi-Fault Programs in Defects4J

Defects4J has enabled numerous software testing and debugging research work since its introduction. A large part of its contribution, and the resulting popularity, lies in the clear separation and distillation of the root cause of each individual test failure based on careful manual analysis, which in turn allowed researchers to easily study individual faults in isolation. However, in a realistic debugging scenario, multiple faults can coexist and affect test results collectively. Study of automated debugging techniques for these situations, such as failure clustering or fault localisation for multiple faults, would significantly benefit from a reliable benchmark of multiple, coexisting faults. We search for versions of Defects4J subjects that contain multiple faults, by iteratively transplanting fault-revealing test cases across Defects4J versions. Out of 326 studied versions of Defects4J subjects, we report that over 95% (311 versions) actually contain from two to 24 faults. We hope that the extended, multi-fault Defects4J can provide a platform for future research of testing and debugging techniques for multi-fault programs.

cs.SE↗

arXiv2021

Improving Test Distance for Failure Clustering with Hypergraph Modelling

Automated debugging techniques, such as Fault Localisation (FL) or Automated Program Repair (APR), are typically designed under the Single Fault Assumption (SFA). However, in practice, an unknown number of faults can independently cause multiple test case failures, making it difficult to allocate resources for debugging and to use automated debugging techniques. Clustering algorithms have been applied to group the test failures according to their root causes, but their accuracy can often be lacking due to the inherent limits in the distance metrics for test cases. We introduce a new test distance metric based on hypergraphs and evaluate their accuracy using multi-fault benchmarks that we have built on top of Defects4J and SIR. Results show that our technique, Hybiscus, can automatically achieve perfect clustering (i.e., the same number of clusters as the ground truth number of root causes, with all failing tests with the same root cause grouped together) for 418 out of 605 test runs with multiple test failures. Better failure clustering also allows us to separate different root causes and apply FL techniques under SFA, resulting in saving up to 82% of the total wasted effort when compared to the state-of-the-art technique for multiple fault localisation.

cs.SE↗

arXiv2021

FDG: A Precise Measurement of Fault Diagnosability Gain of Test Cases

The performance of many Fault Localisation (FL) techniques directly depends on the quality of the used test suites. Consequently, it is extremely useful to be able to precisely measure how much diagnostic power each test case can introduce when added to a test suite used for FL. Such a measure can help us not only to prioritise and select test cases to be used for FL, but also to effectively augment test suites that are too weak to be used with FL techniques. We propose FDG, a new measure of Fault Diagnosability Gain for individual test cases. The design of FDG is based on our analysis of existing metrics that are designed to prioritise test cases for better FL. Unlike other metrics, FDG exploits the ongoing FL results to emphasise the parts of the program for which more information is needed. Our evaluation of FDG with Defects4J shows that it can successfully help the augmentation of test suites for better FL. When given only a few failing test cases (2.3 test cases on average), FDG can effectively augment the given test suite by prioritising the test cases generated automatically by EvoSuite: the augmentation can improve the acc@1 and acc@10 of the FL results by 11.6x and 2.2x on average, after requiring only ten human judgements on the correctness of the assertions EvoSuite generates.

cs.SE↗

arXiv2019

The State and Future of Genetic Improvement

We report the discussion session at the sixth international Genetic Improvement workshop, GI-2019 @ ICSE, which was held as part of the 41st ACM/IEEE International Conference on Software Engineering on Tuesday 28th May 2019. Topics included GI representations, the maintainability of evolved code, automated software testing, future areas of GI research, such as co-evolution, and existing GI tools and benchmarks.

cs.NE↗

arXiv2019

Ahead of Time Mutation Based Fault Localisation using Statistical Inference

Mutation analysis can effectively capture the dependency between source code and test results. This has been exploited by Mutation Based Fault Localisation (MBFL) techniques. However, MBFL techniques suffer from the need to expend the high cost of mutation analysis after the observation of failures, which may present a challenge for its practical adoption. We introduce SIMFL (Statistical Inference for Mutation-based Fault Localisation), an MBFL technique that allows users to perform the mutation analysis in advance before a failure is observed, allowing the amortisation of the analysis cost. SIMFL uses mutants as artificial faults and aims to learn the failure patterns among test cases against different locations of mutations. Once a failure is observed, SIMFL requires either almost no or very small additional cost for analysis, depending on the used inference model. An empirical evaluation using Defects4J shows that SIMFL can successfully localise up to 113 out of 203 studied faults (55%) at the top, and 159 (78%) faults within the top five, significantly outperforming existing MBFL techniques while using the results of mutation analysis that has been undertaken before the test failure. The amortised cost of mutation analysis can be further reduced by mutation sampling: SIMFL retains 80% of its localisation accuracy at the top rank when using only 10% of generated mutants, compared to results obtained without sampling.

cs.SE↗