Metraipolis › archive › dc_e6d05883f8a6
BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL — arXiv:2608.02876
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02876
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:15:26.249Z
- SHA-256 of the archived text
f2f03ab9dea0b3d2271432a98fed4c47670a826f20028b4982afdd53ce70d937- Stable URL of this page
https://metraipolis.com/documento/dc_e6d05883f8a6
How to cite
BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL — arXiv:2608.02876 — arXiv (en), https://arxiv.org/abs/2608.02876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6d05883f8a6 (Metraipolis archive dc_e6d05883f8a6, sha256 f2f03ab9dea0b3d2271432a98fed4c47670a826f20028b4982afdd53ce70d937)
BibTeX
@misc{dce6d05883f8a6,
title = {BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL — arXiv:2608.02876},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02876},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6d05883f8a6; sha256 f2f03ab9dea0b3d2271432a98fed4c47670a826f20028b4982afdd53ce70d937},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tool-using agents do not merely consume observations: their actions determine what arrives next. In agentic text-to-SQL, a broad query can spend context and database work before useful evidence appears, while post-hoc compression cannot recover omitted rows or expended work. We present BAP-SQL, which treats observation formation as a budget-control stage: it estimates query risk, rewrites SQL when useful, and delegates hard limits to an independent runtime shield. Across general 4B, specialized FINER-SQL 4B, and 7B backbones, BAP-SQL improves tight-budget success. On the primary BIRD-derived setting, it gains 3.4/3.6 percentage points over matched SFT while using 4.5/5.0% fewer tokens. Matched retraining and task-level transfer associate the gain with policy-visible planning and budget-sensitive rescue. The benefit attenuates as model capability and budget increase, reverses at the loosest setting, and does not reduce database work. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.02876 — 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 2026-10-31T12:05:52.730Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).