DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation
Summary: DeepPrep uses execution-grounded LLM agents to construct data-preparation pipelines, materializing intermediate tables for runtime feedback. Tree-based reasoning enables non-local revision, while progressive agentic training yields GPT-5-level accuracy at 15× lower inference cost. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Meihao Fan (Renmin University of China)
- 2. Ju Fan (Renmin University of China)
- 3. Yuxin Zhang (Renmin University of China)
- 4. Shaolei Zhang (Renmin University of China)
- 5. Xiaoyong Du (Renmin University of China)
- 6. Jie Song (ByteDance)
- 7. Peng Li (ByteDance)
- 8. Fuxin Jiang (ByteDance)
- 9. Tieying Zhang (ByteDance)
- 10. Jianjun Chen (ByteDance)
BibTeX Citation
@article{fan_vldb26,
title = {{DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation}},
author = {Fan, Meihao and Fan, Ju and Zhang, Yuxin and Zhang, Shaolei and Du, Xiaoyong and Song, Jie and Li, Peng and Jiang, Fuxin and Zhang, Tieying and Chen, Jianjun},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3371--3384},
doi = {10.14778/3836663.3836695},
url = {https://doi.org/10.14778/3836663.3836695},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,497 | Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards | 2026 | SIGMOD | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next