iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917548847529984 |
|---|---|
| author | Le, Dat Le, Duc-Cuong Nguyen, Anh-Son Bui, Tuan-Dung Nguyen, Thu-Trang Nguyen, Son Vo, Hieu Dinh |
| author_facet | Le, Dat Le, Duc-Cuong Nguyen, Anh-Son Bui, Tuan-Dung Nguyen, Thu-Trang Nguyen, Son Vo, Hieu Dinh |
| contents | Automated Machine Learning (AutoML) has improved access to machine learning, yet existing techniques often remain limited in flexibility, transparency, and execution reliability. Code-driven AutoML offers a promising direction by synthesizing executable code for preprocessing, model training, and evaluation. However, current LLM-based approaches frequently generate code that is plausible in text yet brittle in execution, insufficiently grounded in the actual dataset, or restricted to narrow solution paths. In this paper, we introduce iML, a multi-agent code-driven AutoML framework designed around three requirements: executability, problem grounding, and broad exploration of valid solutions. iML first analyzes the task and profiles the data, then synthesizes a structured blueprint that guides modular code generation across multiple implementation tracks, including traditional ML,pretrained adaptation, and custom neural architectures. To improve reliability, iML enforces interface checking, dynamic execution, and iterative debugging during integration. We evaluate iML on MLE-BENCH and the newly introduced iML-BENCH, covering diverse Kaggle-style tasks. On MLE-BENCH, iML attains a 90% valid submission rate and a 45% medal rate, and an APS of 0.82, improving the average standardized performance score (APS) over the LLM-based baselines by 52%-273%. On iML-BENCH, it achieves the highest APS and demonstrates robust performance even when task descriptions are substantially stripped. These results establish iML as a reliable and competitive framework for code-driven AutoML. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13937 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML Le, Dat Le, Duc-Cuong Nguyen, Anh-Son Bui, Tuan-Dung Nguyen, Thu-Trang Nguyen, Son Vo, Hieu Dinh Machine Learning Software Engineering Automated Machine Learning (AutoML) has improved access to machine learning, yet existing techniques often remain limited in flexibility, transparency, and execution reliability. Code-driven AutoML offers a promising direction by synthesizing executable code for preprocessing, model training, and evaluation. However, current LLM-based approaches frequently generate code that is plausible in text yet brittle in execution, insufficiently grounded in the actual dataset, or restricted to narrow solution paths. In this paper, we introduce iML, a multi-agent code-driven AutoML framework designed around three requirements: executability, problem grounding, and broad exploration of valid solutions. iML first analyzes the task and profiles the data, then synthesizes a structured blueprint that guides modular code generation across multiple implementation tracks, including traditional ML,pretrained adaptation, and custom neural architectures. To improve reliability, iML enforces interface checking, dynamic execution, and iterative debugging during integration. We evaluate iML on MLE-BENCH and the newly introduced iML-BENCH, covering diverse Kaggle-style tasks. On MLE-BENCH, iML attains a 90% valid submission rate and a 45% medal rate, and an APS of 0.82, improving the average standardized performance score (APS) over the LLM-based baselines by 52%-273%. On iML-BENCH, it achieves the highest APS and demonstrates robust performance even when task descriptions are substantially stripped. These results establish iML as a reliable and competitive framework for code-driven AutoML. |
| title | iML: Executable, Problem-Grounded, and Broadly Exploratory Code-Driven AutoML |
| topic | Machine Learning Software Engineering |
| url | https://arxiv.org/abs/2602.13937 |