While Large Language Models (LLMs) have shown promise in software engineering, their application to unit testing remains largely confined to isolated test generation or oracle prediction, neglecting the broader challenge of test suite maintenance. We introduce TAM-Eval (Test Automated Maintenance Evaluation), a framework and benchmark designed to evaluate model performance across three core test maintenance scenarios: creation, repair, and updating of test suites. Unlike prior work limited to function-level tasks, TAM-Eval operates at the test file level, while maintaining access to full repository context during isolated evaluation, better reflecting real-world maintenance workflows. Our benchmark comprises 1,539 automatically extracted and validated scenarios from Python, Java, and Go projects. TAM-Eval supports system-agnostic evaluation of both raw LLMs and agentic workflows, using a reference-free protocol based on test suite pass rate, code coverage, and mutation testing. Empirical results indicate that state-of-the-art LLMs have limited capabilities in realistic test maintenance processes and yield only marginal improvements in test effectiveness. We release TAM-Eval as an open-source framework to support future research in automated software testing. Our data and code are publicly available at https://github.com/trndcenter/TAM-Eval.
@article{arxiv.2601.18241,
title = {TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance},
author = {Elena Bruches and Vadim Alperovich and Dari Baturova and Roman Derunets and Daniil Grebenkin and Georgy Mkrtchyan and Oleg Sedukhin and Mikhail Klementev and Ivan Bondarenko and Nikolay Bushkov and Stanislav Moiseev},
journal= {arXiv preprint arXiv:2601.18241},
year = {2026}
}
Comments
Accepted for publication at the 9th Workshop on Validation, Analysis and Evolution of Software Tests (VST 2026), co-located with the the 33rd IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER 2026)