7 papers · 1 filter
DRAGON: Robust Classification for Very Large Collections of Software Repositories
Stefano Balla, Stefano Zacchiroli, Thomas Degueule +2
The ability to automatically classify source code repositories with ''topics'' that reflect their content and purpose is very useful, especially when navigating or searching throug…
Are Coding Agents Generating Over-Mocked Tests? An Empirical Study
Andre Hora, Romain Robbes
Coding agents have received significant adoption in software development recently. Unlike traditional LLM-based code completion tools, coding agents work with autonomy (e.g., invok…
Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity
Romain Robbes, Théo Matricon, Thomas Degueule +2
In 2025, coding agents have seen a very rapid adoption. Coding agents leverage Large Language Models (LLMs) in ways that are markedly different from LLM-based code completion, maki…
Package-Aware Approach for Repository-Level Code Completion in Pharo
Omar Abedelkader, Stéphane Ducasse, Oleksandr Zaitsev +2
Pharo offers a sophisticated completion engine based on semantic heuristics, which coordinates specific fetchers within a lazy architecture. These heuristics can be recomposed to s…
Agentic Much? Adoption of Coding Agents on GitHub
Romain Robbes, Théo Matricon, Thomas Degueule +2
In the first half of 2025, coding agents have emerged as a category of development tools that have very quickly transitioned to the practice. Unlike ''traditional'' code completion…
Client--Library Compatibility Testing with API Interaction Snapshots
Gustave Monce, Thomas Degueule, Jean-Rémy Falleri +1
Modern software development heavily relies on third-party libraries to speed up development and enhance quality. As libraries evolve, they may break the tacit contract established…