CoeusBI: A Comprehensive Interactive Business Intelligence System Powered by LLMs at Baidu
Summary: CoeusBI combines an error-feedback offline view-generation agent with hierarchical schema linking to replace manual semantic modeling and tame wide schemas. A routing agent plus dialect-agnostic deterministic compiler enables accurate, token-efficient multi-turn BI at Baidu scale. (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. Jinqing Lian (Beijing Institute of Technology)
- 2. Chaofan Li (Beijing Institute of Technology)
- 3. Yingxia Shao (Beijing Institute of Technology)
- 4. Ming Wang (Baidu)
- 5. Yang Dong (Baidu)
- 6. Xinyi Liu (Baidu)
- 7. Wei Zhang (Baidu)
- 8. Chaoxian Gui (Baidu)
- 9. Tianqi Wan (Baidu)
- 10. Ming Dong (Baidu)
BibTeX Citation
@article{lian_vldb26,
title = {{CoeusBI: A Comprehensive Interactive Business Intelligence System Powered by LLMs at Baidu}},
author = {Lian, Jinqing and Li, Chaofan and Shao, Yingxia and Wang, Ming and Dong, Yang and Liu, Xinyi and Zhang, Wei and Gui, Chaoxian and Wan, Tianqi and Dong, Ming},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4076--4088},
doi = {10.14778/3827998.3828017},
url = {https://doi.org/10.14778/3827998.3828017},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,117 | NL2SQL is a solved problem... Not! | 2024 | CIDR | 9.0149494e-05 |
| 5,508 | SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence | 2025 | VLDB | 6.0997019e-05 |
Previous
Page 1 / 1
Next