Evolving Executable Pipeline Programs for AutoML with Language Models

2026-08-17 · Sofoklis Kitharidis, Cor J. Veenman, Jan N. van Rijn, Thomas Bäck, Niki van Stein arxiv

Automated machine learning (AutoML) systems search for pipelines within a space of preprocessing operators, learners, and hyper-parameters specified in advance: they can select and tune known components, but cannot produce structure outside that space. We present LACE, an AutoML framework that instead searches over complete executable pipeline programs: an evolutionary loop maintains a population of scikit-learn-compatible Python classes, and a large language model acts as the variation operator. To our knowledge, LACE is the first to formulate general tabular pipeline AutoML this way, evaluated on standardized OpenML tasks under a leakage-controlled protocol that withholds dataset identity from the generator. Because every candidate is ordinary Python, the returned pipeline and the search that produced it can be inspected and edited directly, rather than only through a framework's model objects. On 68 OpenML classification tasks, LACE with GPT-5.4-mini significantly outperforms auto-sklearn, H2O, and a fixed XGBoost baseline, with no detectable difference against AutoGluon, the strongest search-based system evaluated, while covering the full benchmark. Newer tabular foundation models are more accurate on the subset of tasks they support, but apply a fixed pretrained predictor rather than returning an editable task-specific program. LACE's contribution is therefore not raw accuracy but a search space defined by code: complete coverage, pipelines practitioners can reuse directly, and a component set extended by editing the prompt rather than the framework.

📄 PDF Abstract BibTeX arXiv:2608.16416

Code (0)

등록된 구현이 없습니다.

Metalearning Using Structure-rich Pipeline Representations for Better AutoML

2021-03-13 · ICLR Workshop Learning_to_Learn 2021 5 · Anonymous

Automatic machine learning (AutoML) systems have been shown to perform better when they learn from past experience. Examples include Auto-sklearn, which warm-starts the ML pipeline search using existing programs known to…

AutoML reinforcement-learning Reinforcement Learning (RL)tabular-classification

Large Language Models Synergize with Automated Machine Learning

2024-05-06 · Jinglue Xu, Jialong Li, Zhen Liu, Nagar Anthel Venkatesh Suryanarayanan 외

Recently, program synthesis driven by large language models (LLMs) has become increasingly popular. However, program synthesis for machine learning (ML) tasks still poses significant challenges. This paper explores a nov…

AutoML Code Generation Program Synthesis

Online AutoML: An adaptive AutoML framework for online learning

2022-01-24 · Bilge Celik, Prabhant Singh, Joaquin Vanschoren

Automated Machine Learning (AutoML) has been used successfully in settings where the learning task is assumed to be static. In many real-world scenarios, however, the data distribution will evolve over time, and it is ye…

AutoML BIG-bench Machine Learning

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

2026-05-19 · Puyi Wang, Yuhao Wang, Linjie Li, Zhengyuan Yang 외 arxiv

Indoor scene synthesis underpins embodied AI, robotic manipulation, and simulation-based policy evaluation, where a useful scene must specify not only what the environment looks like, but also how its objects are structu…

Indoor Scene Synthesis Scene Generation

Adaptation Strategies for Automated Machine Learning on Evolving Data

2020-06-09 · Bilge Celik, Joaquin Vanschoren

Automated Machine Learning (AutoML) systems have been shown to efficiently build good models for new datasets. However, it is often not clear how well they can adapt when the data evolves over time. The main goal of this…

AutoML Bayesian Optimization BIG-bench Machine Learning