LLMs and Prompting for Unit Test Generation: A Large-Scale Evaluation

Automated unit test generation has been widely studied, with Large Language Models (LLMs) recently showing significant potential. LLMs like GPT-4, trained in vast text and code data, excel in various code-related tasks, including unit test generation. However, existing LLM-based approaches often focus solely on the context within the code itself, such as referenced variables, while neglecting broader task-specific contexts, such as the utility of referring to existing tests of relevant methods in unit test generation. Moreover, in the context of unit test generation, these tools prioritize high code coverage, often at the expense of practical usability, correctness, and maintainability. In response, we propose Reference-Based Retrieval Augmentation , a novel mechanism that extends LLM-based Retrieval-Augmented Generation (RAG) to retrieve relevant information by considering task-specific context. In the unit test generation task, for a given focal method, the reference relationships is defined as the reusability or referentiality of tests between the focal method and other methods. To generate high-quality unit tests for the focal method, the test reference relationships are then used to retrieve relevant methods and their existing unit tests. Specifically, we account for the unique structure of unit tests by dividing the test generation process into Given , When , and Then phases. When generating unit tests for a focal method, we retrieve pre-existing tests of other relevant methods, which can provide valuable insights for any of the Given , When , and Then phases. We implement this approach in a tool called RefTest , which sequentially performs preprocessing, test reference retrieval, and unit test generation, using an incremental strategy in which newly generated tests guide the creation of subsequent ones. We evaluated RefTest on 12 open-source projects with 1515 methods, and the results demonstrate that RefTest consistently outperforms existing tools in terms of correctness, completeness, and maintainability of the generated tests.

Unit testing is crucial for software development and maintenance. Effective unit testing ensures and improves software quality, but writing unit tests is time-consuming and labor-intensive. Recent studies have proposed deep learning (DL) techniques or large language models (LLMs) to automate unit test generation. These models are usually trained or fine-tuned on large-scale datasets. Despite growing awareness of the importance of data quality, there has been limited research on the quality of datasets used for test generation. To bridge this gap, we systematically examine the impact of noise on the performance of learning-based test generation models. We first apply the open card sorting method to analyze the most popular and largest test generation dataset, Methods2Test, to categorize eight distinct types of noise. Further, we conduct detailed interviews with 17 domain experts to validate and assess the importance, reasonableness, and correctness of the noise taxonomy. Then, we propose CleanTest, an automated noise-cleaning framework designed to improve the quality of test generation datasets. CleanTest comprises three filters: a rule-based syntax filter, a rule-based relevance filter, and a model-based coverage filter. To evaluate its effectiveness, we apply CleanTest on two widely-used test generation datasets, i.e., Methods2Test and Atlas. Our findings indicate that 43.52% and 29.65% of datasets contain noise, highlighting its prevalence. Finally, we conduct comparative experiments using four LLMs (i.e., CodeBERT, AthenaTest, StarCoder, and CodeLlama7B) to assess the impact of noise on test generation performance. The results show that filtering noise positively influences the test generation ability of the models. Fine-tuning the four LLMs with the filtered Methods2Test dataset, on average, improves its performance by 67% in branch coverage, using the Defects4J benchmark. For the Atlas dataset, the four LLMs improve branch coverage by 39%. Additionally, filtering noise improves bug detection performance, resulting in a 21.42% increase in bugs detected by the generated tests.

Automated test generation has been extensively studied for dynamically compiled or typed programming languages like Java and Python. However, Go, a popular statically compiled and typed programming language for server application development, has received limited support from existing tools. To address this gap, we present NxtUnit, an automatic unit test generation tool for Go that uses random testing and is well-suited for microservice architecture. NxtUnit employs a random approach to generate unit tests quickly, making it ideal for smoke testing and providing quick quality feedback. It comes with three types of interfaces: an integrated development environment (IDE) plugin, a command-line interface (CLI), and a browser-based platform. The plugin and CLI tool allow engineers to write unit tests more efficiently, while the platform provides unit test visualization and asynchronous unit test generation. We evaluated NxtUnit by generating unit tests for 13 open-source repositories and 500 ByteDance in-house repositories, resulting in a code coverage of 20.74% for in-house repositories. We conducted a survey among Bytedance engineers and found that NxtUnit can save them 48% of the time on writing unit tests. We have made the CLI tool available at https://github.com/bytedance/nxt_unit.

Automatic unit test generation that explores the input space and produces effective test cases for given programs have been studied for decades. Many unit test generation tools that can help generate unit test cases with high structural coverage over a program have been examined. However, the fact that existing test generation tools are mainly evaluated on general software programs calls into question about its practical effectiveness and usefulness for machine learning libraries, which are statistically orientated and have fundamentally different nature and construction from general software projects. In this paper, we set out to investigate the effectiveness of existing unit test generation techniques on machine learning libraries. To investigate this issue, we conducted an empirical study on five widely used machine learning libraries with two popular unit testcase generation tools, i.e., EVOSUITE and Randoop. We find that (1) most of the machine learning libraries do not maintain a high-quality unit test suite regarding commonly applied quality metrics such as code coverage (on average is 34.1%) and mutation score (on average is 21.3%), (2) unit test case generation tools, i.e., EVOSUITE and Randoop, lead to clear improvements in code coverage and mutation score, however, the improvement is limited, and (3) there exist common patterns in the uncovered code across the five machine learning libraries that can be used to improve unit test case generation tasks.

Unit testing has a significant role in software development and its impacts depend on the quality of test cases and test data used. To reduce time and effort, unit test generator systems can help automatically generate test cases and test data. However, there is currently no unit test generator for Kotlin programming language even though this language is popularly used for android application developments. In this study, we propose and develop a test generator system that utilizes genetic algorithm (GA) and ANTLR4 parser. GA is used to obtain the most optimal test cases and data for a given Kotlin code. ANTLR4 parser is used to optimize the mutation process in GA so that the mutation process is not totally random. Our model results showed that the average value of code coverage in generated unit tests against instruction coverage is 95.64%, with branch coverage of 76.19% and line coverage of 96.87%. In addition, only two out of eight generated classes produced duplicate test cases with a maximum of one duplication in each class. Therefore, it can be concluded that our optimization with GA on the unit test generator is able to produce unit tests with high code coverage and low duplication.

Code coverage-guided unit test generation (CGTG) and large language model-based test generation (LLMTG) are two principal approaches for the generation of unit tests. Each of these approaches has its inherent advantages and drawbacks. Tests generated by CGTG have been shown to exhibit high code coverage and high executability. However, they lack the capacity to comprehend code intent, which results in an inability to identify deviations between code implementation and design intent (i.e., functional defects). Conversely, although LLMTG demonstrates an advantage in terms of code intent analysis, it is generally characterized by low executability and necessitates iterative debugging. In order to enhance the ability of unit test generation to identify functional defects, a novel framework has been proposed, entitled the intent analysis-guided unit test generation and refinement (IGTG&R) model. The IGTG&R model consists of a two-stage process for test generation. In the first stage, we introduce coverage path entropy to enhance CGTG to achieve high executability and code coverage of test cases. The second stage refines the test cases using LLMs to identify functional defects. We quantify and verify the interference of incorrect code implementation on intent analysis through conditional entropy. In order to reduce this interference, the focal method body is excluded from the code context information during intent analysis. Using these two-stage process, IGTG&R achieves a more profound comprehension of the intent of the code and the identification of functional defects. The IGTG&R model has been demonstrated to achieve an identification rate of functional defects ranging from 65% to 89%, with an execution success rate of 100% and a code coverage rate of 75.8%. This indicates that IGTG&R is superior to the CGTG and LLMTG approaches in multiple aspects.

Software testing is an important step in the software development lifecycle. One of the main process that take lots of time is developing the test code. We propose an automatic unit test code generation to speed up the process and helps avoiding repetition. We develop the unit test code generator using Lua programming language. Lua is a fast, lightweight, embeddable scripting language. It has been used in many industrial applications with focuses on embedded systems and games. Unlike other popular scripting language like JavaScript, Python, and Ruby, Lua does not have any unit test generator developed to help its software testing process. The final product, Lua unit test generator (LUTG), integrated to one of the most popular Lua IDE, ZeroBrane Studio, as a plugin to seamlessly connect the coding and testing process. The code generator can generate unit test code, save test cases data on Lua and XML file format, and generate the test data automatically using search-based technique, genetic algorithm, to achieve full branch coverage test criteria. Using this generator to test several Lua source code files shows that the developed unit test generator can help the unit testing process. It was expected that the unit test generator can improve productivity, quality, consistency, and abstraction of unit testing process.

A notorious class of concurrency bugs are race condition related to correlated variables, which make up about 30 % of all non-deadlock concurrency bugs. A solution to prevent this problem is the automatic generation of parallel unit tests. This paper presents an approach to generate parallel unit tests for variable correlations in multithreaded code. We introduce a hybrid approach for identifying correlated variables. Furthermore, we estimate the number of potentially violated correlations for methods executed in parallel. In this way, we are capable of creating unit tests that are suited for race detectors considering correlated variables. We were able to identify more than 85 % of all race conditions on correlated variables in eight applications after applying our parallel unit tests. At the same time, we reduced the number of unnecessary generated unit tests. In comparison to a test generator unaware of variable correlations, redundant unit tests are reduced by up to 50 %, while maintaining the same precision and accuracy in terms of the number of detected races.

Unit testing verifies the presence of faults in individual software components. Previous research has been targeting the automatic generation of unit tests through the adoption of random or search-based algorithms. Despite their effectiveness, these approaches aim at creating tests by solely optimizing metrics like code coverage, without ensuring that the resulting tests have granularities that would allow them to verify both the behavior of individual production methods and the interaction between methods of the class under test. To address this limitation, we propose a two-step systematic approach to the generation of unit tests: we first force search-based algorithms to create tests that cover individual methods of the production code, hence implementing the so-called intra-method tests; then, we relax the constraints to enable the creation of intra-class tests that target the interactions among production code methods. The assessment of our approach is conducted through a mixed-method research design that combines statistical analyses with a user study. The key results report that our approach is able to keep the same level of code and mutation coverage while providing test suites that are more structured, more understandable and aligned to the design principles of unit testing.

Service-oriented architecture has evolved to be the backbone for large-scale integration between different applications and platforms. This concept has led to today’s reality of cloud services. Many of the major business platforms are providing their services to end-users and other companies as well. Companies are crafting ways to allow other businesses fast service integration and to get on board quickly in the market. REST (representational state transfer) has emerged as the standard protocol for implementing and consuming these services, which are called RESTful application programming interfaces (APIs). As the internal details of the RESTful APIs are not completely available during consumption, thorough testing has been a major challenge. Any unprecedented change in the APIs can cause the major failure of service operations, which can cause an organization to face both financial and trust losses. Research efforts have been made to alleviate testing challenges by introducing different frameworks and auto-generating unit test approaches. However, there is still a lack of an overview of the state-of-the-art in RESTful API testing. As such, the objective of this article is to identify, analyze, and synthesize the studies that have been performed related to RESTful APIs’ testing methodologies and unit test generation. With this perspective, a systematic literature review (SLR) study was conducted. In total, 16 papers were retrieved and included based on study selection criteria for in-depth analysis. This SLR discusses and categorizes different problems and solutions related to RESTful APIs’ testing and unit test generation.

Unit testing is a fundamental aspect of software development, ensuring the correctness and robustness of code implementations. Traditionally, unit tests are manually crafted by developers based on their understanding of the code and its requirements. However, this process can be time-consuming, errorprone, and may overlook certain edge cases. In recent years, there has been growing interest in leveraging large language models (LLMs) for automating the generation of unit tests. LLMs, such as GPT (Generative Pre-trained Transformer), CodeT5, StarCoder, LLaMA, have demonstrated remarkable capabilities in natural language understanding and code generation tasks. By using LLMs, researchers aim to develop techniques that automatically generate unit tests from code snippets or specifications, thus optimizing the software testing process. This paper presents a literature review of articles that use LLMs for unit test generation tasks. It also discusses the history of the most commonly used large language models and their parameters, including the first time they have been used for code generation tasks. The result of this study presents the large language models for code and unit test generation tasks and their increasing popularity in code generation domain, indicating a great promise for the future of unit test generation using LLMs.

Unit tests are becoming popular. Are there ways to automate the generation of good unit tests? Parameterized unit tests are unit tests that depend on inputs. PUTs describe behavior more concisely than traditional unit tests. We use symbolic execution techniques and constraint solving to find inputs for PUTs that achieve high code coverage, to turn existing unit tests into PUTs, and to generate entirely new PUTs that describe an existing implementation's behavior. Traditional testing benefits from these techniques because test inputs - including the behavior of entire classes - can often be generated automatically from compact PUTs

Unit testing plays a major role in the software development process. What started as an ad hoc approach is becoming a common practice among developers. It enables the immediate detection of bugs introduced into a unit whenever code changes occur. Hence, unit tests provide a safety net of regression tests and validation tests which encourage developers to refactor existing code with greater confidence. One of the major corner stones of the agile development approach is unit testing. Agile methods require all software classes to have unit tests that can be executed by an automated unit-testing framework. However, not all software systems have unit tests. When changes to such software are needed, writing unit tests from scratch, which is hard and tedious, might not be cost effective. In this paper we propose a technique which automatically generates unit tests for software that does not have such tests. We have implemented GenUTest, a prototype tool which captures and logs interobject interactions occurring during the execution of Java programs, using the aspect-oriented language AspectJ. These interactions are used to generate JUnit tests. They also serve in generating mock aspects—mock object-like entities, which enable testing units in isolation. The generated JUnit tests and mock aspects are independent of the tool, and can be used by developers to perform unit tests on the software. Comprehensiveness of the unit tests depends on the software execution. We applied GenUTest to several open source projects such as NanoXML and JODE. We present the results, explain the limitations of the tool, and point out direction to future work to improve the code coverage provided by GenUTest and its scalability.

Unit testing, a common step in software development, presents a challenge. When produced manually, unit test suites are often insufficient to identify defects. The main alternative is to use one of a variety of automatic unit-test generation tools: these are able to produce and execute a large number of test inputs that extensively exercise the unit under test. However, without a priori specifications, programmers need to manually verify the outputs of these test executions, which is generally impractical. To reduce this cost, unit-test selection techniques may be used to help select a subset of automatically generated test inputs. Then programmers can verify their outputs, equip them with test oracles, and put them into the existing test suite. In this paper, we present the operational violation approach for unit-test generation and selection, a black-box approach without requiring a priori specifications. The approach dynamically generates operational abstractions from executions of the existing unit test suite. These operational abstractions guide test generation tools to generate tests to violate them. The approach selects those generated tests violating operational abstractions for inspection. These selected tests exercise some new behavior that has not been exercised by the existing tests. We implemented this approach by integrating the use of Daikon (a dynamic invariant detection tool) and Parasoft Jtest (a commercial Java unit testing tool), and conducted several experiments to assess the approach.

Context. Manual unit test creation is a cognitively intensive and time-consuming activity, prompting researchers and practitioners to increasingly adopt automated testing tools. Recent advancements in language models have expanded automation possibilities, including unit test generation, yet these models raise substantial sustainability concerns due to their energy consumption compared to conventional, specialized tools. Goal. Our research investigates whether the energy overhead associated with employing a small language model (SLM) for unit test generation is justified compared to a conventional, lightweight testing tool. We compare and analyze the energy consumption incurred during test suite generation, as well as the fault-finding effectiveness of the resulting test suites, for an SLM (Phi-3.1 Mini 128k) and Pynguin, a purpose-built tool for unit test generation. Method.We posed two research questions: (i) What is the difference in energy usage between Phi and Pynguin during the generation of unit test suites for Python programs?; and (ii) To what extent do unit test suites generated by Phi and Pynguin differ in their fault-finding effectiveness? To rigorously address the first research question, we employed Bayesian Data Analysis (BDA). For the second research question, we conducted a complementary empirical analysis using descriptive statistics. Results. Our Bayesian analysis provides robust evidence indicating that Phi consistently consumes significantly more energy than Pynguin during test suite generation. Conclusions. These findings underscore significant sustainability concerns associated with employing even SLMs for routine Software Engineering tasks such as unit test generation. The results challenge the assumption of universal energy efficiency benefits from smaller-scale models and emphasize the necessity for careful energy consumption evaluations in the adoption of automated software testing approaches.