arXiv:2608.15389cs.AI2026-08

构建文本转SQL的自主性分类体系与实证基准,统一评估大模型性能。

Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL

  • 按推理自主性从弱到强划分五类生成模式,确保评估可追溯。
  • 8B开源模型在难例上表现提升,但高自主性带来计算成本上升。
  • 链式思考监督主要提升复杂查询准确率,适合进阶研究者参考。

基于大语言模型的文本转SQL研究在异构基准、模型架构和推理协议中进展纷呈,导致跨系统比较困难。本文将其重构为排行榜聚合:收集作者自报指标,并沿推理自主性轴(受限、上下文、迭代、自主代理、内部推理)组织数据,每项结果均可溯源。为锚定评估,我们在Spider数据集上开展聚焦案例研究,对比8B级开源模型在有无思维链(CoT)监督下与少量样本的DeepSeek-V3及GLM-4基线的表现。发现四个规律:Spider在BIRD和Spider-2.0上的迁移能力不均;自主性提升带来鲁棒性但伴随显著代价;内部推理介于仅输出答案与外部调度代理之间;思维链收益集中于难例(Hard)与超难例(Extra-Hard)。我们发布一个Python工具包,映射该自主性轴,未来方法可直接接入排行榜。

原文摘要 · Abstract (English)

LLM-based Text-to-SQL progress is reported across heterogeneous benchmarks, backbones, and inference protocols, making cross-system comparison fragile. We reframe the field as a leaderboard aggregation: we collect the metrics authors themselves report and organize them along an inference-autonomy axis spanning constrained, in-context, iterative, agentic, and reasoning-internalized generation, with traceable provenance for every cell. To anchor the aggregation empirically, we run a focused case study on Spider, comparing 8B open-source backbones with and without chain-of-thought (CoT) supervision against few-shot DeepSeek~V3 and GLM-4 baselines. Four patterns emerge: Spider gains transfer unevenly to BIRD and Spider~2.0; autonomy buys robustness at non-trivial cost; reasoning internalization sits between answer-only decoding and externally orchestrated agents; and CoT gains concentrate on Hard and Extra-Hard queries. We release a Python harness mirroring the autonomy axis so that future methods can be added directly to the leaderboard.

文本转SQL大模型评估推理自主性链式思考

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。