Metraipolis › archive › dc_9a437d47deb2
Large Language Models as a Universal Searcher for Open-World Automated Machine Learning — arXiv:2611.12791
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12791
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:54.758Z
- SHA-256 of the archived text
b23c84de5709c2f76b3b76a9041518de803f1f69ff4c4762f861a1a6e997c305- Stable URL of this page
https://metraipolis.com/documento/dc_9a437d47deb2
How to cite
Large Language Models as a Universal Searcher for Open-World Automated Machine Learning — arXiv:2611.12791 — arXiv (en), https://arxiv.org/abs/2611.12791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9a437d47deb2 (Metraipolis archive dc_9a437d47deb2, sha256 b23c84de5709c2f76b3b76a9041518de803f1f69ff4c4762f861a1a6e997c305)
BibTeX
@misc{dc9a437d47deb2,
title = {Large Language Models as a Universal Searcher for Open-World Automated Machine Learning — arXiv:2611.12791},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12791},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9a437d47deb2; sha256 b23c84de5709c2f76b3b76a9041518de803f1f69ff4c4762f861a1a6e997c305},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.12791 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:52.460Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).