{"slug": "bap-sql-budget-aware-observation-planning-for-agentic-text-to-sql", "title": "BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL", "summary": "BAP-SQL, a budget-aware observation planning method for agentic text-to-SQL, improves tight-budget success by 3.4/3.6 percentage points over matched SFT on the BIRD-derived setting while using 4.5/5.0% fewer tokens, according to a new arXiv paper (arXiv:2608.02876v1). The method estimates query risk, rewrites SQL when useful, and delegates hard limits to an independent runtime shield, with gains attenuating as model capability and budget increase.", "body_md": "arXiv:2608.02876v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/bap-sql-budget-aware-observation-planning-for-agentic-text-to-sql", "canonical_source": "https://arxiv.org/abs/2608.02876", "published_at": "2026-08-05 04:00:00+00:00", "updated_at": "2026-08-05 04:09:37.819027+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-agents"], "entities": ["BAP-SQL", "FINER-SQL", "BIRD"], "alternates": {"html": "https://wpnews.pro/news/bap-sql-budget-aware-observation-planning-for-agentic-text-to-sql", "markdown": "https://wpnews.pro/news/bap-sql-budget-aware-observation-planning-for-agentic-text-to-sql.md", "text": "https://wpnews.pro/news/bap-sql-budget-aware-observation-planning-for-agentic-text-to-sql.txt", "jsonld": "https://wpnews.pro/news/bap-sql-budget-aware-observation-planning-for-agentic-text-to-sql.jsonld"}}