Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL

The paper introduces PlanPool, a method for agentic Text-to-SQL systems to manage clarification questions by maintaining a mutable question pool. By requiring agents to explicitly ask or drop each planned question, PlanPool improves ambiguity coverage and reduces silent failures compared to unconstrained or prompt-based approaches. Experiments on benchmarks derived from BIRD-Interact and Spider show that PlanPool achieves competitive execution accuracy while better handling underspecification.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• agents
• benchmarks
• data-engineering