TY - GEN
T1 - Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity
AU - Robbes, Romain
AU - Matricon, Théo
AU - Degueule, Thomas
AU - Hora, Andre
AU - Zacchiroli, Stefano
N1 - Publisher Copyright:
© 2026 Copyright held by the owner/author(s).
PY - 2026/7/31
Y1 - 2026/7/31
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/105047098430
U2 - 10.1145/3793302.3793375
DO - 10.1145/3793302.3793375
M3 - Conference contribution
AN - SCOPUS:105047098430
T3 - Proceedings - 2026 IEEE/ACM 23rd International Conference on Mining Software Repositories, MSR 2026
SP - 496
EP - 507
BT - Proceedings - 2026 IEEE/ACM 23rd International Conference on Mining Software Repositories, MSR 2026
PB - Association for Computing Machinery, Inc
T2 - 23rd International Conference on Mining Software Repositories, MSR 2026
Y2 - 13 April 2026 through 14 April 2026
ER -