Skip to content
Preprint

Evolving Executable Pipeline Programs for AutoML with Language Models

Aug 2026 · 0 citations · 45 references
Computer Science

TL;DR

This work presents 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.

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.

View source

Similar papers

Review Open access Jul 2026

Automating Machine Learning Pipeline Design via Metalearning

This thesis introduces the Dynamic Pipeline CASH problem, which extends the CASH formulation to incorporate meta-model-driven search space creation for pipelines, using Metalearning (MtL) to dynamically build task-specific search spaces.

Edesio Alcobaça, A. Carvalho · 0 citations
Book Open access Jul 2026

Semantic Mutation via LLMs: A Hybrid Approach to Evolutionary Program Synthesis

This work proposes a hybrid framework that integrates Large Language Models into GP in two complementary roles: as a semantic mutation operator that proposes non-local program rewrites during evolution, and as a post-evolution repair that iteratively refines single failed programs after search terminates.

Woletemaryam Liyew, Dojun Oh, Seokki Lee et al. · 0 citations
#artificial intelligence Preprint Aug 2026

Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services

Flama is presented, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-language-model (LLM) applications that unifies REST API development, predictive model serving, and generative AI inference in one architecture.

José A. Perdiguero López, Miguel A. Durán-Olivencia · 0 citations
Preprint Aug 2026

Code as Representation: A Compilable Parsing Paradigm for Academic Documents

Compilable Academic Document Parsing (CADP) is proposed, a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page.

Rihui Jin, Jun Wang, Chen Zhu et al. · 0 citations
Preprint Aug 2026

Harnessing LLMs for Document-Guided Fuzzing of Python Libraries

Python libraries underpin deep learning, scientific computing, data analysis, and computer vision, making their reliability critical to downstream applications. Testing their APIs requires inputs that satisfy both per-parameter constraints and dependencies among parameters. Existing approaches either leave such constraints implicit in generated programs or rely on library-specific parsing rules. This paper introduces VistaFuzz, a document-guided fuzzing technique that uses a locally served open-sourced LLM to extract parameter specifications from API documents and generate inputs that satisfy both parameter constraints and inter-parameter dependencies. We evaluate VistaFuzz on 7,718 APIs across twelve Python libraries. Inter-parameter relationships occur in 40.1\% of tested APIs, and disabling their resolution reduces the valid generation rate on those APIs from above 95\% to 31.6\%--52.8\%. VistaFuzz reports 74 issues, of which 43 have been confirmed by developers and 29 have been fixed.

Bin Duan, Tarek Mahmud, Meiru Che et al. · 0 citations
Preprint Jul 2026

Benchmarking LLMs on File System Design and Implementation

Large Language Models (LLMs) are fundamentally transforming computer system research and development. As we employ LLMs in file system (fs) development, it is essential to understand their capabilities, limitations, and operational efficiency for domain-specific tasks. We present \phi-Bench, an LLM benchmarking framework for fs-specific tasks. To facilitate benchmarking, we develop six types of tasks in \phi-Bench: basic understanding, basic implementation, performance modeling, debugging, optimization, and new feature development. Each type emphasizes different LLM capabilities: instruction following, knowledge recall, reasoning, or coding. To create high-quality tasks while achieving broad coverage with minimal human effort, we develop a new AI-assisted task generation pipeline in addition to expert-written and textbook-adapted tasks. With 505 tasks in \phi-Bench, we conduct an empirical study with both open source (DeepSeek-V4-Flash, GLM-5.1, and MiniMax-M2.7) and proprietary (Claude-Opus-4.7, GPT-5.2, and Gemini-3.1-Pro) LLMs. Our study discloses the model efficiency for different tasks, causes of failed fs tasks, and techniques for mitigating LLM failures. We will open source \phi-Bench to facilitate public research on using LLMs for fs development.

Yu Xue, Daixuan Li, Jian Huang · 0 citations