Routing End User Queries to Enterprise Databases
This addresses the challenge of efficient query routing in multi-database environments, but it is incremental as it builds on existing NL-to-SQL datasets and methods.
The paper tackles the problem of routing natural language queries to appropriate databases in enterprise settings, showing that a reasoning-driven reranking strategy outperforms baselines across all metrics.
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.