Automated machine learning in the era of large language models: a systematic review of green, trustworthy, and human-centered automation (2020–2026)

Abstract Automated Machine Learning (AutoML) has rapidly transformed the landscape of artificial intelligence by democratizing access to sophisticated machine learning models and streamlining complex development workflows. This systematic review, conducted in accordance with the PRISMA 2020 guidelines, comprehensively analyzes the evolution of AutoML from 2020 to early 2026 (final search conducted in early February 2026), with a particular focus on the integration of Large Language Models (LLMs) and the emerging paradigm of Green AutoML. Based on a systematic search of IEEE Xplore, ACM Digital Library, ScienceDirect, arXiv, and Google Scholar, 103 studies meeting all eligibility criteria were included in the qualitative synthesis. We synthesize key architectural shifts, evaluate the impact of LLMs on the AutoML pipeline, and assess the progress toward sustainable and energy-efficient AI solutions. The review also identifies critical research gaps—especially concerning trustworthiness, interpretability, and human-in-the-loop integration—and proposes a strategic roadmap for future research. Our findings highlight a significant transition from traditional Hyperparameter Optimization (HPO) and Neural Architecture Search (NAS) toward LLM-driven generative AutoML systems, alongside a growing imperative for environmentally conscious AI development. This work provides a structured overview for researchers and practitioners, offering a novel taxonomy of LLM-integrated AutoML systems, a comprehensive evaluation of energy-efficiency metrics, and a roadmap for Human-in-the-Loop (HITL) AutoML. Collectively, these contributions support the development of more robust, ethical, and sustainable automated machine learning solutions.