BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL
Quick Answer
BAP-SQL enhances agentic text-to-SQL by introducing a budget-aware observation planning stage, improving success rates by 3.4-3.6% with 4.5-5.0% fewer tokens across various models.
Quick Take
This approach allows for better query risk estimation and SQL rewriting, optimizing database interaction without increasing workload.
Key Points
- BAP-SQL improves tight-budget success in text-to-SQL tasks.
- Achieves 3.4/3.6 percentage point gains over matched SFT models.
- Reduces token usage by 4.5/5.0% while maintaining database work.
- Utilizes independent runtime shields for budget control.
- Benefits diminish with increased model capability and budget.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | 10 pages, 3 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7; H.2.3 |
| Cite as: | arXiv:2608.02876 [cs.AI] |
| (or arXiv:2608.02876v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02876 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chong Peng [view email]
[v1]
Mon, 3 Aug 2026 20:55:58 UTC (1,451 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.