As Large Language Models (LLMs) demonstrate increasingly sophisticated code processing capabilities, evaluating their performance on engineering-level code remains challenging. Existing repository-level benchmarks primarily focus on single scenarios, such as code generation or bug fixing, without adequately capturing the diversity and complexity of real-world software or project engineering workflows. Furthermore, these benchmarks suffer from limited controllability in question positioning and reliability issues in their generated test cases. To address these limitations, we present CorePipe, a fully automated pipeline that converts repositories into comprehensive test cases, and introduce CoreCodeBench, a configurable multi-scenario repository-level benchmark. To simulate real engineering scenarios, CorePipe generates three types of atomic questions (Development, BugFix, and Test-Driven Development) specifically targeting core code segments. These atomic questions are further combined into three types of composite questions, with difficulty levels flexibly adjusted through hyperparameter tuning. CoreCodeBench provides a comprehensive and extensive repository-level benchmark to investigate the applicability of LLMs in real-world engineering projects. Experiments with 16 LLMs across diverse scenarios reveal varying capabilities and offer multi-dimensional insights into LLM performance in engineering contexts. The code for CorePipe is available at https://github.com/AGI-Eval-Official/CoreCodeBench, and the data for CoreCodeBench can be accessed at https://huggingface.co/collections/tubehhh/corecodebench-68256d2faabf4b1610a08caa.
Large Language Models (LLMs) excel at code generation, but ensuring their outputs to be functionally correct, especially in complex programming tasks, is a persistent challenge. While traditional Test-Driven Development (TDD) offers a path for code refinement, its efficacy with LLMs is often undermined by the scarcity of high-quality test cases or the pitfalls of automated test generation, including biased tests or inaccurate output predictions that can misdirect the correction process. This paper introduces Property-Generated Solver, a novel framework that leverages Property-Based Testing (PBT) to validate high-level program properties or invariants, instead of relying on specific input-output examples. These properties are often simpler to define and verify than directly predicting exhaustive test oracles, breaking the "cycle of self-deception" where tests might share flaws with the code they are meant to validate. Property-Generated Solver employs two collaborative LLM-based agents: a Generator dedicated to code generation and iterative refinement, and a Tester that manages the PBT life-cycle and formulate semantically rich feedback from property violations. The resulting comprehensive and actionable feedback then guides the Generator in its refinement efforts. By establishing PBT as the core validation engine within this iterative, closed-loop paradigm, Property-Generated Solver provides a robust mechanism for steering LLMs towards more correct and generalizable code. Extensive experimental results on multiple code generation benchmarks demonstrate that Property-Generated Solver achieves substantial pass@1 improvements, ranging from 23.1% to 37.3% relative gains over established TDD methods.
We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests, which inherently encapsulate high-level requirements. The core of **SWE-Flow** is the construction of a Runtime Dependency Graph (RDG), which precisely captures function interactions, enabling the generation of a structured, step-by-step *development schedule*. At each step, **SWE-Flow** produces a partial codebase, the corresponding unit tests, and the necessary code modifications, resulting in fully verifiable TDD tasks. With this approach, we generated 16,061 training instances and 2,020 test instances from real-world GitHub projects, creating the **SWE-Flow-Eval** benchmark. Our experiments show that fine-tuning open model on this dataset significantly improves performance in TDD-based coding. To facilitate further research, we release all code, datasets, models, and Docker images at [Github](https://github.com/Hambaobao/SWE-Flow).
Developing safety-critical automotive software presents significant challenges due to increasing system complexity and strict regulatory demands. This paper proposes a novel framework integrating Generative Artificial Intelligence (GenAI) into the Software Development Lifecycle (SDLC). The framework uses Large Language Models (LLMs) to automate code generation in languages such as C++, incorporating safety-focused practices such as static verification, test-driven development and iterative refinement. A feedback-driven pipeline ensures the integration of test, simulation and verification for compliance with safety standards. The framework is validated through the development of an Adaptive Cruise Control (ACC) system. Comparative benchmarking of LLMs ensures optimal model selection for accuracy and reliability. Results demonstrate that the framework enables automatic code generation while ensuring compliance with safety-critical requirements, systematically integrating GenAI into automotive software engineering. This work advances the use of AI in safety-critical domains, bridging the gap between state-of-the-art generative models and real-world safety requirements.
We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks, where test cases serve as both prompt and verification for code generation. Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases, reflecting real-world software development practices. Comprising 1000 diverse challenges across 20 application domains, the benchmark evaluates LLMs on their ability to generate compact, functional code under the constraints of context length and multi-feature complexity. Our findings highlight instruction following and in-context learning as critical capabilities for TDD success, surpassing the importance of general coding proficiency or pretraining knowledge. Through comprehensive evaluation of 19 frontier models, we reveal performance bottlenecks, such as instruction loss in long prompts, and provide a detailed error analysis spanning multiple root causes. This work underscores the practical value of TDD-specific benchmarks and lays the foundation for advancing LLM capabilities in rigorous, application-driven coding scenarios.
While there has been plenty of work on generating tests from existing code, there has been limited work on generating tests from issues. A correct test must validate the code patch that resolves the issue. This paper focuses on the scenario where that code patch does not yet exist. Doing so supports two major use-cases. First, it supports TDD (test-driven development), the discipline of "test first, write code later" that has well-documented benefits for human software engineers. Second, it also validates SWE (software engineering) agents, which generate code patches for resolving issues. This paper introduces TDD-Bench-Verified, a benchmark for generating tests from issues, and Otter, an LLM-based solution for this task. Otter augments LLMs with rule-based analysis to check and repair their outputs, and introduces a novel self-reflective action planner. Experiments show Otter outperforming state-of-the-art systems for generating tests from issues, in addition to enhancing systems that generate patches from issues. We hope that Otter helps make developers more productive at resolving issues and leads to more robust, well-tested code.
This manuscript signals a new era in the integration of artificial intelligence with software engineering, placing machines at the pinnacle of coding capability. We present a formalized, iterative methodology proving that AI can fully replace human programmers in all aspects of code creation and refinement. Our approach, combining large language models with formal verification, test-driven development, and incremental architectural guidance, achieves a 38.6% improvement over the current top performer's 48.33% accuracy on the SWE-bench benchmark. This surpasses previously assumed limits, signaling the end of human-exclusive coding and the rise of autonomous AI-driven software innovation. More than a technical advance, our work challenges centuries-old assumptions about human creativity. We provide robust evidence of AI superiority, demonstrating tangible gains in practical engineering contexts and laying the foundation for a future in which computational creativity outpaces human ingenuity.
Test-driven development (TDD) is the practice of writing tests first and coding later, and the proponents of TDD expound its numerous benefits. For instance, given an issue on a source code repository, tests can clarify the desired behavior among stake-holders before anyone writes code for the agreed-upon fix. Although there has been a lot of work on automated test generation for the practice "write code first, test later", there has been little such automation for TDD. Ideally, tests for TDD should be fail-to-pass (i.e., fail before the issue is resolved and pass after) and have good adequacy with respect to covering the code changed during issue resolution. This paper introduces TDD-Bench Verified, a high-quality benchmark suite of 449 issues mined from real-world GitHub code repositories. The benchmark's evaluation harness runs only relevant tests in isolation for simple yet accurate coverage measurements, and the benchmark's dataset is filtered both by human judges and by execution in the harness. This paper also presents Auto-TDD, an LLM-based solution that takes as input an issue description and a codebase (prior to issue resolution) and returns as output a test that can be used to validate the changes made for resolving the issue. Our evaluation shows that Auto-TDD yields a better fail-to-pass rate than the strongest prior work while also yielding high coverage adequacy. Overall, we hope that this work helps make developers more productive at resolving issues while simultaneously leading to more robust fixes.
When it was first introduced, the Chips-n-Salsa Java library provided stochastic local search and related algorithms, with a focus on self-adaptation and parallel execution. For the past four years, we expanded its scope to include evolutionary computation. This paper concerns the evolutionary algorithms that Chips-n-Salsa now provides, which includes multiple evolutionary models, common problem representations, a wide range of mutation and crossover operators, and a variety of benchmark problems. Well-defined Java interfaces enable easily integrating custom representations and evolutionary operators, as well as defining optimization problems. Chips-n-Salsa's evolutionary algorithms include implementations with adaptive mutation and crossover rates, as well as both sequential and parallel execution. Source code is maintained on GitHub, and immutable artifacts are regularly published to the Maven Central Repository to enable easily importing into projects for reproducible builds. Effective development processes such as test-driven development, as well as a variety of static analysis tools help ensure code quality.
Large Language Models (LLMs) have enabled the emergence of LLM agents: autonomous systems capable of achieving under-specified goals and adapting post-deployment, often without explicit code or model changes. Evaluating these agents is critical to ensuring their performance and safety, especially given their dynamic, probabilistic, and evolving nature. However, traditional approaches such as predefined test cases and standard redevelopment pipelines struggle to address the unique challenges of LLM agent evaluation. These challenges include capturing open-ended behaviors, handling emergent outcomes, and enabling continuous adaptation over the agent's lifecycle. To address these issues, we propose an evaluation-driven development approach, inspired by test-driven and behavior-driven development but reimagined for the unique characteristics of LLM agents. Through a multivocal literature review (MLR), we synthesize the limitations of existing LLM evaluation methods and introduce a novel process model and reference architecture tailored for evaluation-driven development of LLM agents. Our approach integrates online (runtime) and offline (redevelopment) evaluations, enabling adaptive runtime adjustments and systematic iterative refinement of pipelines, artifacts, system architecture, and LLMs themselves. By continuously incorporating evaluation results, including fine-grained feedback from human and AI evaluators, into each stage of development and operation, this framework ensures that LLM agents remain aligned with evolving goals, user needs, and governance standards.
This paper compares the impact of Test-Driven Development (TDD) and Behavior-Driven Development (BDD) on software delivery effectiveness within enterprise environments. Using a qualitative research design, data were collected through in-depth interviews with developers and project managers from enterprises adopting TDD or BDD. Moreover, the findings reveal distinct effects of each model on delivery speed, software quality, and team collaboration. Specifically, TDD emphasizes early testing and iterative development, leading to enhanced code quality and fewer defects, while BDD improves cross-functional communication by focusing on behavior specifications that involve stakeholders directly. However, TDD may create a higher initial time investment, and BDD might encounter challenges in requirement clarity. These differences highlight gaps in understanding how each model aligns with varying project types and stakeholder needs, which can guide enterprises in selecting the most suitable model for their unique requirements. The study contributes to the literature by providing insights into the practical application and challenges of TDD and BDD, suggesting future research on their long-term impacts in diverse settings.
Behavior-driven development (BDD) is an Agile testing methodology fostering collaboration among developers, QA analysts, and stakeholders. In this manuscript, we propose a novel approach to enhance BDD practices using large language models (LLMs) to automate acceptance test generation. Our study uses zero and few-shot prompts to evaluate LLMs such as GPT-3.5, GPT-4, Llama-2-13B, and PaLM-2. The paper presents a detailed methodology that includes the dataset, prompt techniques, LLMs, and the evaluation process. The results demonstrate that GPT-3.5 and GPT-4 generate error-free BDD acceptance tests with better performance. The few-shot prompt technique highlights its ability to provide higher accuracy by incorporating examples for in-context learning. Furthermore, the study examines syntax errors, validation accuracy, and comparative analysis of LLMs, revealing their effectiveness in enhancing BDD practices. However, our study acknowledges that there are limitations to the proposed approach. We emphasize that this approach can support collaborative BDD processes and create opportunities for future research into automated BDD acceptance test generation using LLMs.
Recent Large Language Models (LLMs) have demonstrated significant capabilities in generating code snippets directly from problem statements. This increasingly automated process mirrors traditional human-led software development, where code is often written in response to a requirement. Historically, Test-Driven Development (TDD) has proven its merit, requiring developers to write tests before the functional code, ensuring alignment with the initial problem statements. Applying TDD principles to LLM-based code generation offers one distinct benefit: it enables developers to verify the correctness of generated code against predefined tests. This paper investigates if and how TDD can be incorporated into AI-assisted code-generation processes. We experimentally evaluate our hypothesis that providing LLMs like GPT-4 and Llama 3 with tests in addition to the problem statements enhances code generation outcomes. We experimented with established function-level code generation benchmarks such as MBPP and HumanEval. Our results consistently demonstrate that including test cases leads to higher success in solving programming challenges. We assert that TDD is a promising paradigm for helping ensure that the code generated by LLMs effectively captures the requirements.
Unit testing frameworks are nowadays considered a best practice, included in almost all modern software development processes, to achieve rapid development of correct specifications. Knowledge representation and reasoning paradigms such as Answer Set Programming (ASP), that have been used in industry-level applications, are not an exception. Indeed, the first unit testing specification language for ASP was proposed in 2011 as a feature of the ASPIDE development environment. Later, a more portable unit testing language was included in the LANA annotation language. In this paper we revisit both languages and tools for unit testing in ASP. We propose a new unit test specification language that allows one to inline tests within ASP programs, and we identify the computational complexity of the tasks associated with checking the various program-correctness assertions. Test-case specifications are transparent to the traditional evaluation, but can be interpreted by a specific testing tool. Thus, we present a novel environment supporting test driven development of ASP programs.
The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, hindering the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance. However, the intrinsic defects in a big model may be inherited by the compressed one. Such defects may be easily leveraged by adversaries, since a compressed model is usually deployed in a large number of devices without adequate protection. In this article, we aim to address the safe model compression problem from the perspective of safety-performance co-optimization. Specifically, inspired by the test-driven development (TDD) paradigm in software engineering, we propose a test-driven sparse training framework called SafeCompress. By simulating the attack mechanism as safety testing, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm. Then, considering two kinds of representative and heterogeneous attack mechanisms, i.e., black-box membership inference attack and white-box membership inference attack, we develop two concrete instances called BMIA-SafeCompress and WMIA-SafeCompress. Further, we implement another instance called MMIA-SafeCompress by extending SafeCompress to defend against the occasion when adversaries conduct black-box and white-box membership inference attacks simultaneously. We conduct extensive experiments on five datasets for both computer vision and natural language processing tasks. The results show the effectiveness and generalizability of our framework. We also discuss how to adapt SafeCompress to other attacks besides membership inference attack, demonstrating the flexibility of SafeCompress.
In today's society, we are becoming increasingly dependent on software systems. However, we also constantly witness the negative impacts of buggy software. Program synthesis aims to improve software correctness by automatically generating the program given an outline of the expected behavior. For decades, program synthesis has been an active research field, with recent approaches looking to incorporate Large Language Models to help generate code. This paper explores the concept of LLM4TDD, where we guide Large Language Models to generate code iteratively using a test-driven development methodology. We conduct an empirical evaluation using ChatGPT and coding problems from LeetCode to investigate the impact of different test, prompt and problem attributes on the efficacy of LLM4TDD.
Large language models (LLMs) have demonstrated unparalleled prowess in mimicking human-like text generation and processing. Among the myriad of applications that benefit from LLMs, automated code generation is increasingly promising. The potential to transform natural language prompts into executable code promises a major shift in software development practices and paves the way for significant reductions in manual coding efforts and the likelihood of human-induced errors. This paper reports the results of a study that evaluates the performance of various LLMs, such as Bard, ChatGPT-3.5, ChatGPT-4, and Claude-2, in generating Python for coding problems. We focus on how levels of prompt specificity impact the accuracy, time efficiency, and space efficiency of the generated code. A benchmark of 104 coding problems, each with four types of prompts with varying degrees of tests and specificity, was employed to examine these aspects comprehensively. Our results indicate significant variations in performance across different LLMs and prompt types, and its key contribution is to reveal the ideal prompting strategy for creating accurate Python functions. This study lays the groundwork for further research in LLM capabilities and suggests practical implications for utilizing LLMs in automated code generation tasks and test-driven development.
The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, which hinders the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance. However, the intrinsic defects in the big model may be inherited by the compressed one. Such defects may be easily leveraged by attackers, since the compressed models are usually deployed in a large number of devices without adequate protection. In this paper, we try to address the safe model compression problem from a safety-performance co-optimization perspective. Specifically, inspired by the test-driven development (TDD) paradigm in software engineering, we propose a test-driven sparse training framework called SafeCompress. By simulating the attack mechanism as the safety test, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm. Further, considering a representative attack, i.e., membership inference attack (MIA), we develop a concrete safe model compression mechanism, called MIA-SafeCompress. Extensive experiments are conducted to evaluate MIA-SafeCompress on five datasets for both computer vision and natural language processing tasks. The results verify the effectiveness and generalization of our method. We also discuss how to adapt SafeCompress to other attacks besides MIA, demonstrating the flexibility of SafeCompress.
We introduce the TimeGym Forecasting Debugging Toolkit, a Python library for testing and debugging time series forecasting pipelines. TimeGym simplifies the testing forecasting pipeline by providing generic tests for forecasting pipelines fresh out of the box. These tests are based on common modeling challenges of time series. Our library enables forecasters to apply a Test-Driven Development approach to forecast modeling, using specified oracles to generate artificial data with noise.
Automated unit test case generation tools facilitate test-driven development and support developers by suggesting tests intended to identify flaws in their code. Existing approaches are usually guided by the test coverage criteria, generating synthetic test cases that are often difficult for developers to read or understand. In this paper we propose AthenaTest, an approach that aims to generate unit test cases by learning from real-world focal methods and developer-written testcases. We formulate unit test case generation as a sequence-to-sequence learning task, adopting a two-step training procedure consisting of denoising pretraining on a large unsupervised Java corpus, and supervised finetuning for a downstream translation task of generating unit tests. We investigate the impact of natural language and source code pretraining, as well as the focal context information surrounding the focal method. Both techniques provide improvements in terms of validation loss, with pretraining yielding 25% relative improvement and focal context providing additional 11.1% improvement. We also introduce Methods2Test, the largest publicly available supervised parallel corpus of unit test case methods and corresponding focal methods in Java, which comprises 780K test cases mined from 91K open-source repositories from GitHub. We evaluate AthenaTest on five defects4j projects, generating 25K passing test cases covering 43.7% of the focal methods with only 30 attempts. We execute the test cases, collect test coverage information, and compare them with test cases generated by EvoSuite and GPT-3, finding that our approach outperforms GPT-3 and has comparable coverage w.r.t. EvoSuite. Finally, we survey professional developers on their preference in terms of readability, understandability, and testing effectiveness of the generated tests, showing overwhelmingly preference towards AthenaTest.