Djamel Eddine Khelladi

Jean-Baptiste Döderlein, Nguessan Hermann Kouadio, Mathieu Acher et al.

Language models are promising solutions for tackling increasing complex problems. In software engineering, they recently gained attention in code assistants, which generate programs from a natural language task description (prompt). They have the potential to save time and effort but remain poorly understood, limiting their optimal use. In this article, we investigate the impact of input variations on two configurations of a language model, focusing on parameters such as task description, surrounding context, model creativity, and the number of generated solutions. We design specific operators to modify these inputs and apply them to three LLM-based code assistants (Copilot, Codex, StarCoder2) and two benchmarks representing algorithmic problems (HumanEval, LeetCode). Our study examines whether these variations significantly affect program quality and how these effects generalize across models. Our results show that varying input parameters can greatly improve performance, achieving up to 79.27% success in one-shot generation compared to 22.44% for Codex and 31.1% for Copilot in default settings. Actioning this potential in practice is challenging due to the complex interplay in our study - the optimal settings for temperature, prompt, and number of generated solutions vary by problem. Reproducing our study with StarCoder2 confirms these findings, indicating they are not model-specific. We also uncover surprising behaviors (e.g., fully removing the prompt can be effective), revealing model brittleness and areas for improvement.

Jean-Baptiste Döderlein, Djamel Eddine Khelladi, Mathieu Acher et al.

Programming environments typically separate the world of static code from the dynamic execution of programs. Developers must switch between writing code and observing its execution, often with limited tools to understand the relationship between code changes and runtime behavior. Several paradigms and approaches exist to bridge this gap, including exploratory programming for comparing code variants, live programming for immediate feedback, and omniscient debugging for exploring execution history. However, existing solutions tend to focus on specific aspects and one specific paradigm rather than providing a fully integrated environment with multiple capabilities. This paper introduces \spacetime Programming, a novel approach that unifies these paradigms to create a programming model for exploring both code modifications and execution flow. At the core of our approach is a trace mechanism that captures not only execution state but also the corresponding code changes, enabling developers to explore programs in both space (code variants) and time (execution flow). As a proof of concept, we implemented a Python library supporting SpaceTime Programming and applied it in two contexts: a live omniscient debugger and a Pygame game development tool, showcased through a Flappy Bird-like game. We further evaluated SpaceTimePy on five real-world Python projects, finding performance overhead ranging from 35% to 150% on test suites.

Heraldo Borges, Juliana Alves Pereira, Djamel Eddine Khelladi et al.

Configuring the Linux kernel to meet specific requirements, such as binary size, is highly challenging due to its immense complexity-with over 15,000 interdependent options evolving rapidly across different versions. Although several studies have explored sampling strategies and machine learning methods to understand and predict the impact of configuration options, the literature still lacks a comprehensive and large-scale dataset encompassing multiple kernel versions along with detailed quantitative measurements. To bridge this gap, we introduce LinuxData, an accessible collection of kernel configurations spanning several kernel releases, specifically from versions 4.13 to 5.8. This dataset, gathered through automated tools and build processes, comprises over 240,000 kernel configurations systematically labeled with compilation outcomes and binary sizes. By providing detailed records of configuration evolution and capturing the intricate interplay among kernel options, our dataset enables innovative research in feature subset selection, prediction models based on machine learning, and transfer learning across kernel versions. Throughout this paper, we describe how the dataset has been made easily accessible via OpenML and illustrate how it can be leveraged using only a few lines of Python code to evaluate AI-based techniques, such as supervised machine learning. We anticipate that this dataset will significantly enhance reproducibility and foster new insights into configuration-space analysis at a scale that presents unique opportunities and inherent challenges, thereby advancing our understanding of the Linux kernel's configurability and evolution.

Charly Reux, Mathieu Acher, Djamel Eddine Khelladi et al.

With the rise of AI-based code generation, customizing existing code out of natural language instructions to modify visual results -such as figures or images -has become possible, promising to reduce the need for deep programming expertise. However, even experienced developers can struggle with this task, as it requires identifying relevant code regions (feature location), generating valid code variants, and ensuring the modifications reliably align with user intent. In this paper, we introduce vTikZ, the first benchmark designed to evaluate the ability of Large Language Models (LLMs) to customize code while preserving coherent visual outcomes. Our benchmark consists of carefully curated vTikZ editing scenarios, parameterized ground truths, and a reviewing tool that leverages visual feedback to assess correctness. Empirical evaluation with stateof-the-art LLMs shows that existing solutions struggle to reliably modify code in alignment with visual intent, highlighting a gap in current AI-assisted code editing approaches. We argue that vTikZ opens new research directions for integrating LLMs with visual feedback mechanisms to improve code customization tasks in various domains beyond TikZ, including image processing, art creation, Web design, and 3D modeling.

Djamel Eddine Khelladi, Charly Reux, Mathieu Acher

Large language model (LLM)-based test generation has gained attention in software engineering, yet most studies evaluate LLMs' ability to generate unit tests in a single attempt for a given language, missing the opportunity to leverage LLM diversity for more robust testing. This paper introduces PolyTest, a novel approach that enhances test generation by exploiting polyglot and temperature-controlled diversity. PolyTest systematically leverages these properties in two complementary ways: (1) Cross-lingual test generation, where tests are generated in multiple languages at zero temperature and then unified; (2) Diverse test sampling, where multiple test sets are generated within the same language at a higher temperature before unification. A key insight is that LLMs can generate diverse yet contradicting tests -- same input, different expected outputs -- across languages and generations. PolyTest mitigates inconsistencies by unifying test sets, fostering self-consistency and improving overall test quality. Unlike single-language or single-attempt approaches, PolyTest enhances testing without requiring on-the-fly execution, making it particularly beneficial for weaker-performing languages. We evaluate PolyTest on Llama3-70B, GPT-4o, and GPT-3.5 using EvalPlus, generating tests in five languages (Java, C, Python, JavaScript, and a CSV-based format) at temperature 0 and sampling multiple sets at temperature 1. We observe that LLMs frequently generate contradicting tests across settings, and that PolyTest significantly improves test quality across all considered metrics -- number of tests, passing rate, statement/branch coverage (up to +9.01%), and mutation score (up to +11.23%). Finally, PolyTest outperforms Pynguin in test generation, passing rate, and mutation score.