Author

Jun-Quan Gu

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensembling

SAGE-Loop is proposed, a reliable closed-loop, self-adaptive, LLM-driven AutoML framework that performs multi-round generation and validation for trial-and-repair, and adaptively selects ensemble strategies in both supervised and unsupervised tasks, thereby unifying how to generate with how to use models.

Jun-Quan Gu, Shi-Bo Cui, Xiang-Feng Luo et al. · 0 citations