As software systems have grown in size and complexity, the costs of maintaining such systems increases steadily. In the early 2000's, IBM launched the autonomic computing initiative to mitigate this problem by injecting feedback control mechanisms into software systems to enable them to observe their health and self-heal without human intervention and thereby cope with certain changes in their requirements and environments. Self-healing is one of several fundamental challenges addressed and includes software systems that are able to recover from failure conditions. There has been considerable research on software architectures with feedback loops that allow a multi-component system to adjust certain parameters automatically in response to changes in its environment. However, modifying the components' source code in response to failures remains an open and formidable challenge. Automatic program repair techniques aim to create and apply source code patches autonomously. These techniques have evolved over the years to take advantage of advancements in programming languages, such as reflection. However, these techniques require mechanisms to evaluate if a candidate patch solves the failure condition. Some rely on test cases that capture the context under which the program failed---the patch applied can then be considered as a successful patch if the test result changes from failing to passing. Although test cases are an effective mechanism to govern the applicability of potential patches, the automatic generation of test cases for a given scenario has not received much attention. ReCrash represents the only known implementation to generate test cases automatically with promising results through the use of low-level instrumentation libraries. The work reported in this thesis aims to explore this area further and under a different light. It proposes the use of Aspect-Oriented Programming (AOP)---and in particular of AspectJ---as a higher-level paradigm to express the code elements on which monitoring actions can be interleaved with the source code, to create a representation of the context at the most relevant moments of the execution, so that if the code fails, the contextual representation is retained and used at a later time to automatically write a test case. By doing this, the author intends to contribute to fill the gap that prevents the use of automatic program repair techniques in a self-healing architecture. The prototype implementation engineered as part of this research was evaluated along three dimensions: memory usage, execution time and binary size. The evaluation results suggest that (1) AspectJ introduces significant overhead with respect to execution time, (2) the implementation algorithm causes a tremendous strain on garbage collection, and (3) AspectJ incorporates tens of additional lines of code, which account for a mean size increase to every binary file of a factor of ten compared to the original size. The comparative analysis with ReCrash shows that the algorithm and data structures developed in this thesis produce more thorough test cases than ReCrash. Most notably, the solution presented here mitigates ReCrash's current inability to reproduce environment-specific failure conditions derived from on-demand instantiation. This work can potentially be extended to apply in less-intrusive frameworks that operate at the same level as AOP to address the shortcomings identified in this analysis. / Graduate

Most of previous program repair approaches are only able to generate fixes for one-line bugs, including machine learning based approaches. This work aims to reveal whether such a system with the state of the art technique is able to make useful predictions while being fed by whole source files. To verify whether multi-line bugs can be fixed using a state of the art solution a system has been created, using already existing Neural Machine Translation tools and data gathered from GitHub. The result of the finished system shows however, that the method used in this thesis is not sufficient to get satisfying results. No bug has successfully been corrected by the system. Although the results are poor there are still unexplored approaches to the project that possibly could improve the performance of the system. One way being narrowing down the input data to method level of source code instead of file level.

C# provides static analysis libraries for template-based code analysis and code fixing. These libraries have been used by the open-source community to generate numerous NuGet packages for different use-cases. However, due to the unstructured vastness of these packages, it is difficult to find the ones required for a project and creating new analyzers and fixers take time and effort to create. Therefore, this thesis proposes a neural network, which firstly imitates existing fixers and secondly extrapolates to fixes of unseen diagnostics. To do so, the state-of-the-art of static analysis NuGet packages is examined and further used to generate a dataset with diagnostics and corresponding code fixes for 24,622 data points. Since many C# fixers apply formatting changes, all formatting is preserved in the dataset. Furthermore, since the fixers also apply identifier changes, the tokenization of the dataset is varied between splitting identifiers by camelcase and preserving them. The neural network uses a sequence-to-sequence learning approach with the Transformer model and takes file context, diagnostic message and location as input and predicts a diff as output. It is capable of imitating 46.3% of the fixes, normalized by diagnostic type, and for data points with unseen diagnostics, it is able to extrapolate to 11.9% of normalized data points. For both experiments, splitting identifiers by camelcase produces the best results. Lastly, it is found that a higher proportion of formatting tokens in input has minimal positive impact on prediction success rates, whereas the proportion of formatting in output has no impact on success rates. / C# tillhandahåller statiska analysbibliotek för mallbaserad kodanalys och kodfixering. Dessa bibliotek har använts av open source-gemenskapen för att generera många NuGet-paket för olika användningsfall. Men på grund av mängden av dessa paket är det svårt att hitta de som krävs för ett projekt och att skapa nya analysatorer och fixare tar tid och ansträngning att skapa. Därför föreslår denna avhandling ett neuralt nätverk, som för det första imiterar befintliga korrigeringar och för det andra extrapolerar till korrigeringar av osynlig diagnostik. För att göra det har det senaste inom statisk analys NuGetpaketen undersökts och vidare använts för att generera en datauppsättning med diagnostik och motsvarande kodfixar för 24 622 datapunkter. Eftersom många C# fixers tillämpar formateringsändringar, bevaras all formatering i datasetet. Dessutom, eftersom fixarna också tillämpar identifieringsändringar, varieras tokeniseringen av datamängden mellan att dela upp identifierare efter camelcase och att bevara dem. Det neurala nätverket använder en sekvenstill- sekvens-inlärningsmetod med Transformer-modellen och tar filkontext, diagnostiskt meddelande och plats som indata och förutsäger en skillnad som utdata. Den kan imitera 46,3% av korrigeringarna, normaliserade efter diagnostisk typ, och för datapunkter med osynlig diagnostik kan den extrapolera till 11,9% av normaliserade datapunkter. För båda experimenten ger uppdelning av identifierare efter camelcase de bästa resultaten. Slutligen har det visat sig att en högre andel formateringstokens i indata har minimal positiv inverkan på åndelen korrekta förutsägelser, medan andelen formatering i utdata inte har någon inverkan på åndelen korrekta förutsägelser.

Research shows that grammatical mistakes in a sentence can be corrected by machine translating it to another language and back. We investigate whether this correction capability of Large Language Models (LLMs) extends to Automatic Program Repair (APR), a software engineering task. Current generative models for APR are pre-trained on source code and fine-tuned for repair. This paper proposes bypassing fine-tuning and using Round-Trip Translation (RTT): translation of code from one programming language to another programming or natural language, and back. We hypothesize that RTT with LLMs performs a regression toward the mean, which removes bugs as they are a form of noise w.r.t. the more frequent, natural, bug-free code in the training data. To test this hypothesis, we employ eight recent LLMs pre-trained on code, including the latest GPT versions, and four common program repair benchmarks in Java. We find that RTT with English as an intermediate language repaired 101 of 164 bugs with GPT-4 on the HumanEval-Java dataset. Moreover, 46 of these are unique bugs that are not repaired by other LLMs fine-tuned for APR. Our findings highlight the viability of round-trip translation with LLMs as a technique for automated program repair and its potential for research in software engineering. / Forskning visar att grammatiska fel i en mening kan korrigeras genom att maskinöversätta den till ett annat språk och tillbaka. Vi undersöker om denna korrigeringsegenskap hos stora språkmodeller (LLMs) även gäller för Automatisk Programreparation (APR), en uppgift inom mjukvaruteknik. Nuvarande generativa modeller för APR är förtränade på källkod och finjusterade för reparation. Denna artikel föreslår att man undviker finjustering och använder Tur och retur-översättning (RTT): översättning av kod från ett programmeringsspråk till ett annat programmerings- eller naturspråk, och tillbaka. Vi antar att RTT med LLMs utför en regression mot medelvärdet, vilket tar bort buggar eftersom de är en form av brus med avseende på den mer frekventa, naturliga, buggfria koden i träningsdatan. För att testa denna hypotes använder vi åtta nyligen förtränade LLMs på kod, inklusive de senaste GPT-versionerna, och fyra vanliga programreparationsstandarder i Java. Vi upptäcker att RTT med engelska som ett mellanspråk reparerade 101 av 164 buggar med GPT-4 på HumanEval-Java-datasetet. Dessutom är 46 av dessa unika buggar som inte repareras av andra LLMs finjusterade för APR. Våra resultat belyser genomförbarheten av tur och retur-översättning med LLMs som en teknik för automatiserad programreparation och dess potential för forskning inom mjukvaruteknik.

This thesis investigates how Large Language Models can be used to repair Solidity Smart Contracts automatically through the main contribution of this thesis, the Transformative Repair Tool. The Transformative Repair Tool achieves similar results to current state-of-the-art tools on the Smartbugs Curated Dataset and is the first published tool that uses Large Language Models to repair Solidity Smart Contracts. Moreover, the thesis explores different prompt strategies to repair Smart Contracts and assess their performance. / Detta masterexamensarbete undersöker hur stora språkmodeller kan användas för att automatisk laga solidity smarta kontrakt genom verktyget Transformative Repair Tool, som är detta masterexamensarbete huvudsakliga bidrag. Transformative Repair Tool presterar liknande som dagens bästa verktyg inom automatisk lagning av smarta kontrakt på Smartbugs Curated datasettet och är det första publicerade verktyget som just använder stora språkmodeller för att reparera solidity smarta kontrakt. Dessutom så utforskar denna rapport olika textprompts och dess prestanda för att laga smarta kontrakt