English

Routing End User Queries to Enterprise Databases

Artificial Intelligence 2026-01-28 v1 Databases

Abstract

We address the task of routing natural language queries in multi-database enterprise environments. We construct realistic benchmarks by extending existing NL-to-SQL datasets. Our study shows that routing becomes increasingly challenging with larger, domain-overlapping DB repositories and ambiguous queries, motivating the need for more structured and robust reasoning-based solutions. By explicitly modelling schema coverage, structural connectivity, and fine-grained semantic alignment, the proposed modular, reasoning-driven reranking strategy consistently outperforms embedding-only and direct LLM-prompting baselines across all the metrics.

Keywords

Cite

@article{arxiv.2601.19825,
  title  = {Routing End User Queries to Enterprise Databases},
  author = {Saikrishna Sudarshan and Tanay Kulkarni and Manasi Patwardhan and Lovekesh Vig and Ashwin Srinivasan and Tanmay Tulsidas Verlekar},
  journal= {arXiv preprint arXiv:2601.19825},
  year   = {2026}
}

Comments

6 pages, 2 figures

R2 v1 2026-07-01T09:22:37.458Z