cs.CLNov 9, 2026

Large Language Models as a Universal Searcher for Open-World Automated Machine Learning

Authors: Yuxuan Hu, Jihao Liu, Weikang Shi, Xijie Huang, Linda Wei, Mingjie Zhan, Aojun Zhou, Rui Liu, 

Organizations: Multimedia Laboratory (CUHK MMLab), The Chinese University of Hong Kong, Shatin, Hong Kong · Shenzhen Loop Area Institute, Shenzhen, China

Abstract

Developing effective machine learning models requires complex manual tuning, while current Automated Machine Learning (AutoML) frameworks remain domain-specific and isolate model architecture, training hyperparameter, and data ratio optimization. Here, we bridge this gap by proposing a universal, large language model (LLM)-based AutoML framework that jointly optimizes these configurations for the first time without the need for task-specific fine-tuning. We propose NCode, a unified numerical encoding scheme that translates diverse AutoML design choices into universal discrete sequences and effectively reframes the optimization process as a unified ranking task. Trained solely on optimization trajectories derived from a limited, single-domain vision task, the proposed LLM-based searcher demonstrates impressive cross-task, cross-modality and joint search-space optimization generalizability, achieving state-of-the-art performance across image classification, image segmentation, speaker verification and text-to-image benchmarks. Crucially, it exhibits superior scalability in the large-scale training and joint optimization of a billion-parameter Diffusion Transformer, requiring 896 GPU-days and attaining a state-of-the-art GenEval score of 0.91. By leveraging reinforcement learning to instill Chain-of-Thought reasoning, we provide a systematic way to interpret the LLM-based searcher's internal decision-making mechanisms, revealing its optimization strategy shifted from the early-stage diversity-driven exploration to the late-stage anchor exploitation. Our proposed framework provides a scalable, generalizable, and interpretable pathway toward general-purpose open-world machine learning optimization.

Figures & tables

Explore similar work

CardsList
  1. Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch

    Mar 25, 2026Fabio Ferreira, Lucca Wobbe, Arjun Krishnakumar +2Hyperparameter OptimizationLarge Language Model-Guided Optimization

  2. Evolving Executable Pipeline Programs for AutoML with Language Models

    Aug 17, 2026Sofoklis Kitharidis, Cor J. Veenman, Jan N. van Rijn +2Automated Machine LearningTabular ML

  3. AutoAdapt: An Automated Domain Adaptation Framework for LLMs

    Mar 9, 2026Sidharth Sinha, Anson Bastos, Xuchao Zhang +3Domain Adaptation for LLMsDomain Adaptation