mlsanityData to 7 Oct 2026

BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL

arXiv 2608.02876 ↗First posted 3 Aug 2026cs.AIcited by 1

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 30 of its 32 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

30 of 32 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026AgentSM: Semantic Memory for Agentic Text-to-SQL22 Jan
  2. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL2 Nov

Other references · 28

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  5. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2017Safe Reinforcement Learning via Shieldingcited by 427
  8. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 381
  9. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 279
  10. 2024Token-Budget-Aware LLM Reasoningcited by 242
  11. 2025Online Difficulty Filtering for Reasoning Oriented Reinforcement Learningcited by 100
  12. 2025Acting Less is Reasoning More! Teaching Model to Act Efficientlycited by 80
16 more
  1. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 67
  2. 2018Learned Cardinalities: Estimating Correlated Joins with Deep Learningcited by 64
  3. 2018Robust Text-to-SQL Generation with Execution-Guided Decodingcited by 51
  4. 2025Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learningcited by 51
  5. 2025Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewardscited by 25
  6. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 17
  7. 2021A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumerationcited by 14
  8. 2025EllieSQL: Cost-Efficient Text-to-SQL with Complexity-Aware Routingcited by 13
  9. 2026ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agentscited by 13
  10. 2026BAGEN: Are LLM Agents Budget-Aware?cited by 12
  11. 2025MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQLcited by 10
  12. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  13. 2026SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQLcited by 7
  14. 2025LpBound: Pessimistic Cardinality Estimation using ℓp-Norms of Degree Sequencescited by 2
  15. 2025SQLGovernor: An LLM-powered SQL Toolkit for Real World Applicationcited by 2
  16. 2025Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQLcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQLcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
  2. 2025Budget-Aware Tool Use Enables Effective Agent Scaling
  3. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
  4. 2026CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation
  5. 2026BudgetBench: A Budget-Tiered Protocol and Pilot Harness for Memory Strategy Evaluation in Local Large Language Model Agents
  6. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
  7. 2026RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution
  8. 2026ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents