1 citations · 2 across the 9 of their papers we have counts for
11 papers
Externalized CPDAG Summaries Improve LLM Causal Deduction
Wentao Sun, João Paulo Nogueira, Dominique Verchere +2
Corr2Cause asks whether a causal claim holds in every DAG compatible with observed correlations and conditional independencies. We frame this as latent-object reasoning: the label…
Spec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation
Jean-Baptiste Espinasse, Djamel Eddine Khelladi, Mathieu Acher
COBOL remains widely deployed, yet representative corpora reflecting real production code are rarely available, limiting rigorous benchmarking of modernization approaches. We propo…
Code Transformation Rule Synthesis using LLMs: Potential and Limits
Axel Allain, Aymeric Blot, Djamel Eddine Khelladi +1
Due to their black-box nature, LLMs suffer from limited explain- ability and a lack of determinism. Their usage cost can also rise, particularly with repetitive tasks on large code…
Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines
Mathieu Acher, Jean-Marc Jézéquel
Frontier coding agents now promise end-to-end authorship of complete software systems. Two empirical questions follow: can AI coding-agent teammates program in any target language,…
Imperfect Visual Verification for Code Edition : A Case Study on TikZ
Charly Reux, Mathieu Acher, Djamel Eddine Khelladi +2
LLMs have significantly advanced code generation, enabling the synthesis of functional programs. While recent systems achieve strong performance on many coding benchmarks, tasks in…
Small Yet Configurable: Unveiling Null Variability in Software
Xhevahire Tërnava, Georges Aaron Randrianaina, Luc Lesoil +1
Many small-scale software systems, that is, with limited codebase or binary size, are widely used in everyday tasks, yet their configurability remains largely unexplored. At the sa…
SpaceTime Programming: Live and Omniscient Exploration of Code and Execution
Jean-Baptiste Döderlein, Djamel Eddine Khelladi, Mathieu Acher +1
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…
LLM Code Customization with Visual Results: A Benchmark on TikZ
Charly Reux, Mathieu Acher, Djamel Eddine Khelladi +2
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,…
Linux Kernel Configurations at Scale: A Dataset for Performance and Evolution Analysis
Heraldo Borges, Juliana Alves Pereira, Djamel Eddine Khelladi +1
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 evolvin…
Unify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs
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 fo…
Exploring Performance Trade-offs in JHipster
Edouard Guégain, Alexandre Bonvoisin, Clément Quinton +2
The performance of software systems remains a persistent concern in the field of software engineering. While traditional metrics like binary size and execution time have long been…