Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity

International Conference on Mining Software Repositories (MSR) 2026 Open access

Read full text
Authors: Romain Robbes, Théo Matricon, Thomas Degueule, André Hora, Stefano Zacchiroli
DOI: 10.1145/3793302.3793375
Cited by: 0

Abstract

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, making their study critical. Moreover, unlike LLM-based completion, coding agents leave visible traces in software repositories, enabling the use of MSR techniques to study their impact on SE practices. This paper documents the promises, perils, and heuristics that we have gathered from studying coding agent activity on GitHub.

Fields of Study & Subjects

Software Engineering Research Software Engineering Techniques and Practices Open Source Software Innovations

Publication details

Journal / source
International Conference on Mining Software Repositories (MSR)
Pages
496–507
Publication date
13 April 2026
Language
EN