Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity
Year: 2026
Type: conference-paper
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.
Institutions: Centre National de la Recherche Scientifique, Université de Bordeaux, Laboratoire Bordelais de Recherche en Informatique, Institut Polytechnique de Bordeaux, Institut national de recherche en sciences et technologies du numérique, Institut de Recherche en Informatique et Systèmes Aléatoires, Université de Rennes, Universidade Federal de Minas Gerais, Télécom Paris, Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Université de Bordeaux
OpenAlex ID: W7127338189
FWCI:
Cites:
Cited by:
Related to: