发表机构
Microsoft; Carnegie Mellon University; Georgia Institute of Technology（微软公司; 卡内基梅隆大学; 佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
BAP-SQL是面向智能体Text-to-SQL的预算感知观测规划方法，通过将观测形成作为预算控制阶段，在紧预算下提升了SQL生成成功率，同时减少了token使用量。
AI 中文摘要
使用工具的智能体并非仅被动接收观测，其动作会决定后续获取的信息。在智能体Text-to-SQL任务中，宽泛的查询会在有用证据出现前消耗上下文和数据库资源，而事后压缩无法恢复已省略的行或已消耗的工作。我们提出BAP-SQL，将观测形成视为预算控制阶段：它会估计查询风险，在有需要时重写SQL，并将硬限制委托给独立的运行时防护层。在通用4B模型、专用FINER-SQL 4B模型及7B模型骨干上，BAP-SQL提升了紧预算下的成功率。在源自BIRD的主要设置中，它相比匹配的SFT分别提升了3.4/3.6个百分点，同时减少了4.5/5.0%的token使用量。匹配的再训练和任务级迁移表明，该提升与策略可见的规划及预算敏感的救援相关。随着模型能力和预算增加，收益会减弱，在最宽松设置下会反转，且不会减少数据库工作。
英文摘要
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.
Comments10 pages, 3 figures
