Evolving Executable Pipeline Programs for AutoML with Language Models

• URL: http://arxiv.org/abs/2608.16416v1
• Date: Mon, 17 Aug 2026 11:15:25 GMT
• Title: Evolving Executable Pipeline Programs for AutoML with Language Models
• Abstract summary: We present LACE, an AutoML framework that searches over complete executable pipeline programs.<n>An evolutionary loop maintains a population of scikit-learn-compatible Python classes, and a large language model acts as the variation operator.<n>Because every candidate is ordinary Python, the returned pipeline and the search that produced it can be inspected and edited directly.
• Score: 6.598013423021166
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• stratum: A System Infrastructure for Massive Agent-Centric ML Workloads [8.123450153690424]
  Large language models (LLMs) generate, validate, and optimize complete machine learning (ML) pipelines.<n>The existing Python-based ML ecosystem is built around libraries such as Panda scikit-learn.<n>We propose stratum, a unified system infrastructure that decouples pipeline execution from planning and reasoning.
  arXiv  Detail & Related papers  (2026-03-03T23:43:12Z)
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints [59.645885492637845]
  SOPBench is an evaluation pipeline that transforms each service-specific SOP code program into a directed graph of executable functions.<n>Our approach transforms each service-specific SOP code program into a directed graph of executable functions and requires agents to call these functions based on natural language SOP descriptions.<n>We evaluate 18 leading models, and results show the task is challenging even for top-tier models.
  arXiv  Detail & Related papers  (2025-03-11T17:53:02Z)
• AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML [56.565200973244146]
  Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline.<n>Recent works have started exploiting large language models (LLM) to lessen such burden.<n>This paper proposes AutoML-Agent, a novel multi-agent framework tailored for full-pipeline AutoML.
  arXiv  Detail & Related papers  (2024-10-03T20:01:09Z)
• forester: A Tree-Based AutoML Tool in R [0.0]
  The forester is an open-source AutoML package implemented in R for training high-quality tree-based models. It fully supports binary and multiclass classification, regression, and partially survival analysis tasks. With just a few functions, the user is capable of detecting issues regarding the data quality, preparing the preprocessing pipeline, training and tuning tree-based models, evaluating the results, and creating the report for further analysis.
  arXiv  Detail & Related papers  (2024-09-07T10:39:10Z)
• Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
  We introduce the framework of verbalized machine learning (VML)<n>VML constrains the parameter space to be human-interpretable natural language.<n>We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
  arXiv  Detail & Related papers  (2024-06-06T17:59:56Z)
• SubStrat: A Subset-Based Strategy for Faster AutoML [5.833272638548153]
  SubStrat is an AutoML optimization strategy that tackles the data size, rather than configuration space. It wraps existing AutoML tools, and instead of executing them directly on the entire dataset, SubStrat uses a genetic-based algorithm to find a small subset. It then employs the AutoML tool on the small subset, and finally, it refines the resulted pipeline by executing a restricted, much shorter, AutoML process on the large dataset.
  arXiv  Detail & Related papers  (2022-06-07T07:44:06Z)
• SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions [28.718446733713183]
  We propose an AutoML SapientML that can learn from a corpus of existing datasets and their human-written pipelines. We have created a training corpus of 1094 pipelines spanning 170 datasets, and evaluated SapientML on a set of 41 benchmark datasets. Our evaluation shows that SapientML produces the best or comparable accuracy on 27 of the benchmarks while the second best tool fails to even produce a pipeline on 9 of the instances.
  arXiv  Detail & Related papers  (2022-02-18T20:45:47Z)
• VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition [57.06900573003609]
  VolcanoML is a framework that decomposes a large AutoML search space into smaller ones. It supports a Volcano-style execution model, akin to the one supported by modern database systems. Our evaluation demonstrates that, not only does VolcanoML raise the level of expressiveness for search space decomposition in AutoML, it also leads to actual findings of decomposition strategies.
  arXiv  Detail & Related papers  (2021-07-19T13:23:57Z)
• PyGlove: Symbolic Programming for Automated Machine Learning [88.15565138144042]
  We introduce a new way of programming AutoML based on symbolic programming. Under this paradigm, ML programs are mutable, thus can be manipulated easily by another program. We show that PyGlove users can easily convert a static program into a search space, quickly iterate on the search spaces and search algorithms, and craft complex search flows.
  arXiv  Detail & Related papers  (2021-01-21T19:05:44Z)
• Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution [1.5224436211478214]
  This paper describes a novel grammar-based framework that adapts Dynamic Structured Grammatical Evolution (DSGE) to the evolution of Scikit-Learn classification pipelines. The experimental results include comparing AutoML-DSGE to another grammar-based AutoML framework, Resilient ClassificationPipeline Evolution (RECIPE)
  arXiv  Detail & Related papers  (2020-04-01T09:31:34Z)
• AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data [120.2298620652828]
  We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models. Tests on a suite of 50 classification and regression tasks from Kaggle and the OpenML AutoML Benchmark reveal that AutoGluon is faster, more robust, and much more accurate.
  arXiv  Detail & Related papers  (2020-03-13T23:10:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.