Metraipolis › archive › dc_a192fd8bdee8
Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL — arXiv:2610.02739
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02739
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:51:33.552Z
- SHA-256 of the archived text
ce735f93aedab6b3e2ea551460c972916fe6fe91be7a3d88c119505f7ecc2524- Stable URL of this page
https://metraipolis.com/documento/dc_a192fd8bdee8
How to cite
Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL — arXiv:2610.02739 — arXiv, https://arxiv.org/abs/2610.02739 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a192fd8bdee8 (Metraipolis archive dc_a192fd8bdee8, sha256 ce735f93aedab6b3e2ea551460c972916fe6fe91be7a3d88c119505f7ecc2524)
BibTeX
@misc{dca192fd8bdee8,
title = {Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL — arXiv:2610.02739},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02739},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a192fd8bdee8; sha256 ce735f93aedab6b3e2ea551460c972916fe6fe91be7a3d88c119505f7ecc2524},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02739. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic Text-to-SQL systems can interact with users to clarify underspecified queries before generating SQL. However, a correct execution result does not necessarily imply that the agent has adequately resolved the underlying underspecification: the agent may silently make unverified assumptions that happen to match the intended answer. We show that this behavior is driven in part by premature clarification termination. Although forcing an agent to ask more questions improves execution accuracy, ambiguities are concentrated in earlier interactions, making brute-force questioning inefficient. More importantly, even when explicitly prompted to plan its clarification process, the agent frequently abandons questions that it has already identified as relevant. To address this failure mode, we introduce PlanPool, which externalizes the clarification plan as a mutable question pool. Every planned question must be explicitly asked or dropped before submission, while newly discovered ambiguities can be added during interaction. Across three benchmarks derived from BIRD-Interact and Spider, PlanPool consistently improves ambiguity coverage and reduces silent failures over unconstrained and prompt-based alternatives, while maintaining competitive execution accuracy. Our results highlight an important distinction in agentic reasoning: identifying missing information is not sufficient, and the agent must also reliably maintain and resolve it before committing to an answer. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.02739 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T22:46:10.546Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).