arXiv subjects

Zacharie Chenail-Larcher

Publications and source records attributed to Zacharie Chenail-Larcher.

3 recordsLinked to original sources

arXiv2026

LLM Code Smells: A Taxonomy and Detection Approach

Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and ability to simulate human reasoning to some extent. However, poor integration of LLM inference in source code can undermine software system quality. Therefore, inadequate LLM integration coding practices must be documented to help developers mitigate such issues. Following our earlier work on LLM code smells, this paper consolidates and refines the concept by presenting a self-contained taxonomy and a catalog of nine LLM code smells. We also create SpecDetect4LLM, a static source code analysis tool for their detection, and conduct extensive empirical evaluations of its detection effectiveness (precision and recall) as well as the prevalence of LLM code smells across 692 open-source software projects (171,194 source files). Our results show that LLM code smells affect 73.5% of the analyzed systems, with a detection precision of 91.3% and a recall of 71.8%.

cs.SE↗

arXiv2026

GLiSE: A Prompt-Driven and ML-Powered Tool for Automated Grey Literature Extraction in Software Engineering

Grey literature is essential to software engineering research as it captures practices and decisions that rarely appear in academic venues. However, collecting and assessing it at scale remains difficult because of their heterogeneous sources, formats, and APIs that impede reproducible, large-scale synthesis. To address this issue, we present GLiSE, a prompt-driven tool that turns a research topic prompt into platform-specific queries, gathers results from common software-engineering web sources (GitHub, Stack Overflow) and Google Search, and uses embedding-based semantic classifiers to filter and rank results according to their relevance. GLiSE is designed for reproducibility with all settings being configuration-based, and every generated query being accessible. In this paper, (i) we present the GLiSE tool, (ii) provide a curated dataset of software engineering grey-literature search results classified by semantic relevance to their originating search intent, and (iii) conduct an empirical study on the usability of our tool.

cs.SE↗

arXiv2025

Specification and Detection of LLM Code Smells

Large Language Models (LLMs) have gained massive popularity in recent years and are increasingly integrated into software systems for diverse purposes. However, poorly integrating them in source code may undermine software system quality. Yet, to our knowledge, there is no formal catalog of code smells specific to coding practices for LLM inference. In this paper, we introduce the concept of LLM code smells and formalize five recurrent problematic coding practices related to LLM inference in software systems, based on relevant literature. We extend the detection tool SpecDetect4AI to cover the newly defined LLM code smells and use it to validate their prevalence in a dataset of 200 open-source LLM systems. Our results show that LLM code smells affect 60.50% of the analyzed systems, with a detection precision of 86.06%.

cs.SE↗