# Evolving Executable Pipeline Programs for AutoML with Language Models

arXiv: https://arxiv.org/abs/2608.16416 · HTML: https://mlsanity.com/paper/2608.16416/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [FLAML: A Fast and Lightweight AutoML Library](https://mlsanity.com/paper/1911.04706/) (2019)
- [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024)
- [AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML](https://mlsanity.com/paper/2410.02958/) (2024)
- [AutoML-GPT: Automatic Machine Learning with GPT](https://mlsanity.com/paper/2305.02499/) (2023)
- [Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science](https://mlsanity.com/paper/1603.06212/) (2016)
- [MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks](https://mlsanity.com/paper/2304.14979/) (2023)
- [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025)
- [R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science](https://mlsanity.com/paper/2505.14738/) (2025)
- [In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics](https://mlsanity.com/paper/2410.16309/) (2024)
- [LLM Guided Evolution -- The Automation of Models Advancing Models](https://mlsanity.com/paper/2403.11446/) (2024)
- [BLADE: Benchmark suite for LLM-driven Automated Design and Evolution of iterative optimisation heuristics](https://mlsanity.com/paper/2504.20183/) (2025)

## Abstract (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.