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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Robbes, Romain, Matricon, Théo, Degueule, Thomas, Hora, Andre, Zacchiroli, Stefano
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908793909018624
author Robbes, Romain
Matricon, Théo
Degueule, Thomas
Hora, Andre
Zacchiroli, Stefano
author_facet Robbes, Romain
Matricon, Théo
Degueule, Thomas
Hora, Andre
Zacchiroli, Stefano
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18345
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity
Robbes, Romain
Matricon, Théo
Degueule, Thomas
Hora, Andre
Zacchiroli, Stefano
Software Engineering
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.
title Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity
topic Software Engineering
url https://arxiv.org/abs/2601.18345