DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation
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_ | 1866914313737863168 |
|---|---|
| author | Fan, Meihao Fan, Ju Zhang, Yuxin Zhang, Shaolei Du, Xiaoyong Song, Jie Li, Peng Jiang, Fuxin Zhang, Tieying Chen, Jianjun |
| author_facet | Fan, Meihao Fan, Ju Zhang, Yuxin Zhang, Shaolei Du, Xiaoyong Song, Jie Li, Peng Jiang, Fuxin Zhang, Tieying Chen, Jianjun |
| contents | Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large language models (LLMs) to automate data preparation from natural language specifications. However, existing LLM-powered methods either make decisions without grounding in intermediate execution results, or rely on linear interaction processes that offer limited support for revising earlier decisions. To address these limitations, we propose DeepPrep, an LLM-powered agentic system for autonomous data preparation. DeepPrep constructs data preparation pipelines through iterative, execution-grounded interaction with an environment that materializes intermediate table states and returns runtime feedback. To overcome the limitations of linear interaction, DeepPrep organizes pipeline construction with tree-based agentic reasoning, enabling structured exploration and non-local revision based on execution feedback. To enable effective learning of such behaviors, we propose a progressive agentic training framework, together with data synthesis that supplies diverse and complex ADP tasks. Extensive experiments show that DeepPrep achieves data preparation accuracy comparable to strong closed-source models (e.g., GPT-5) while incurring 15x lower inference cost, while establishing state-of-the-art performance among open-source baselines and generalizing effectively across diverse datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07371 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation Fan, Meihao Fan, Ju Zhang, Yuxin Zhang, Shaolei Du, Xiaoyong Song, Jie Li, Peng Jiang, Fuxin Zhang, Tieying Chen, Jianjun Databases Data preparation, which aims to transform heterogeneous and noisy raw tables into analysis-ready data, remains a major bottleneck in data science. Recent approaches leverage large language models (LLMs) to automate data preparation from natural language specifications. However, existing LLM-powered methods either make decisions without grounding in intermediate execution results, or rely on linear interaction processes that offer limited support for revising earlier decisions. To address these limitations, we propose DeepPrep, an LLM-powered agentic system for autonomous data preparation. DeepPrep constructs data preparation pipelines through iterative, execution-grounded interaction with an environment that materializes intermediate table states and returns runtime feedback. To overcome the limitations of linear interaction, DeepPrep organizes pipeline construction with tree-based agentic reasoning, enabling structured exploration and non-local revision based on execution feedback. To enable effective learning of such behaviors, we propose a progressive agentic training framework, together with data synthesis that supplies diverse and complex ADP tasks. Extensive experiments show that DeepPrep achieves data preparation accuracy comparable to strong closed-source models (e.g., GPT-5) while incurring 15x lower inference cost, while establishing state-of-the-art performance among open-source baselines and generalizing effectively across diverse datasets. |
| title | DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation |
| topic | Databases |
| url | https://arxiv.org/abs/2602.07371 |