Drama: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries
Summary: Drama: an end-to-end paradigm and multi-agent system (DramaBot) that unifies open‑domain data retrieval, structured transformation, and analytic reasoning to answer NL analytic queries. Evaluated on DramaBench (100 QA/verification tasks), DramaBot achieves 86.5% accuracy at $0.05, outperforming baselines up to 6.9× while costing <1/6. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Chuxuan Hu (University of Illinois Urbana-Champaign)
- 2. Maxwell Yang (University of Illinois Urbana-Champaign)
- 3. James Weiland (University of Illinois Urbana-Champaign)
- 4. Yeji Lim (University of Illinois Urbana-Champaign)
- 5. Suhas Palawala (University of Illinois Urbana-Champaign)
- 6. Daniel Kang (University of Illinois Urbana-Champaign)
BibTeX Citation
@inproceedings{hu_sigmod26,
title = {{Drama: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries}},
author = {Hu, Chuxuan and Yang, Maxwell and Weiland, James and Lim, Yeji and Palawala, Suhas and Kang, Daniel},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769781},
url = {https://dl.acm.org/doi/10.1145/3769781},
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 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 279 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB | 0.00022468369 |
| 1,343 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB | 0.00011095866 |
| 2,809 | Text2SQL is Not Enough: Unifying AI and Databases with TAG | 2025 | CIDR | 8.0994951e-05 |
| 9,466 | LEAP: LLM-powered End-to-end Automatic Library for Processing Social Science Queries on Unstructured Data | 2025 | VLDB | 5.2634238e-05 |
Previous
Page 1 / 1
Next