[论文解读] APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

Bowen Cao, Weibin Liao+4 more|arXiv (Cornell University)|Feb 11, 2026

Semantic Web and Ontologies被引用 0

一句话总结

APEX-SQL 引入面向文本到 SQL 的代理探测，以真实数据为依据来支撑推理，从而在大规模企业数据库中改善模式链接与 SQL 生成。在 BIRD 和 Spider 2.0-Snow 上通过假设-验证循环、逻辑规划、双通道修剪、并行数据画像，以及确定性指引检索等方法超越基线。

ABSTRACT

Text-to-SQL systems powered by Large Language Models have excelled on academic benchmarks but struggle in complex enterprise environments. The primary limitation lies in their reliance on static schema representations, which fails to resolve semantic ambiguity and scale effectively to large, complex databases. To address this, we propose APEX-SQL, an Agentic Text-to-SQL Framework that shifts the paradigm from passive translation to agentic exploration. Our framework employs a hypothesis-verification loop to ground model reasoning in real data. In the schema linking phase, we use logical planning to verbalize hypotheses, dual-pathway pruning to reduce the search space, and parallel data profiling to validate column roles against real data, followed by global synthesis to ensure topological connectivity. For SQL generation, we introduce a deterministic mechanism to retrieve exploration directives, allowing the agent to effectively explore data distributions, refine hypotheses, and generate semantically accurate SQLs. Experiments on BIRD (70.65% execution accuracy) and Spider 2.0-Snow (51.01% execution accuracy) demonstrate that APEX-SQL outperforms competitive baselines with reduced token consumption. Further analysis reveals that agentic exploration acts as a performance multiplier, unlocking the latent reasoning potential of foundation models in enterprise settings. Ablation studies confirm the critical contributions of each component in ensuring robust and accurate data analysis.

研究动机与目标

• 推动从被动的基于模式的提示转向主动、数据落地的 Text-to-SQL 推理，在大型、复杂数据库中的应用。

提出的方法

• 提出一个统一的代理文本到 SQL 框架，具备针对模式链接和 SQL 生成的假设-验证循环。

实验结果

研究问题

• RQ1 在真实数据支撑下的代理探索是否能提升大型企业数据库中模式链接的召回率和精确度？
• RQ2 相较于基线，在企业级基准测试上，该代理方法是否提升 SQL 生成的准确性与效率？

主要发现

• APEX-SQL 在 BIRD 与 Spider 基准测试上实现了最先进的模式链接性能（例如，在子集上具有较高的严格召回）。
• 在 SQL 生成方面，APEX-SQL 在 BIRD-Dev 与 Spider 2.0-Snow 的执行准确性上超越竞争基线，且 token 消耗显著下降。
• 代理探索作为性能放大器，解锁企业场景中基础模型的潜在推理能力。
• 消融研究证实逻辑规划、修剪以及确定性指引对于鲁棒数据分析与查询综合的重要性。