ESQ‑Bench is an Oracle‑first NL2SQL benchmark that introduces systematic complexity tiers and silent‑divergence evaluation across three enterprise schema levels. It provides six populated schemas (465 tables, 164,682 rows) on Oracle, PostgreSQL, MySQL, and SQL Server, along with 550 gold‑validated question‑query pairs and a four‑metric evaluation harness. The benchmark reveals that state‑of‑the‑art models such as GPT‑4o and Claude Sonnet 4.6 experience significant drops in execution accuracy and high silent‑divergence rates as schema complexity increases, highlighting a gap between closed‑API models and open‑weight baselines on enterprise Oracle schemas.
By Sanjay Mishra, Divya Chukkapalli, Ganesh R. Naik
The paper argues that retrieval‑augmented question‑answering systems should perform semantic compilation at ingest time rather than re‑deriving meaning at query time. By building a maintained structure—incrementally updated embeddings and validated atomic claims—read operations become far cheaper, with experimental results showing higher accuracy and lower token usage compared to traditional chunk‑based retrieval. The authors present two proofs: cheaper incremental updates and superior performance on broadcast‑interview transcripts, suggesting a new systems agenda for compilation and read planning.
By Kyle Wild, Yusuke Takahashi, Asako Uraki
BudgetSchemaBench is a diagnostic tool for evaluating how different schema‑context budgets affect text‑to‑SQL systems. It automatically derives relevance labels from gold SQL, tests four budgets across 80 databases, and compares three schema representations while keeping table rankings fixed. The study shows that increasing the budget improves execution accuracy, especially for lexical retrieval, and that dense retrieval already captures most needed tables at low budgets.
By Chen Shen
arXiv:2606. 28387v1 Announce Type: cross Abstract: Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context.
By Adarsh Agrawal, Shashank Indukuri
arXiv:2606. 28601v1 Announce Type: cross Abstract: Recent progress in Text-to-SQL has been driven by stronger language models and prompting strategies, yet performance on real enterprise benchmarks such as Spider 2.
By Jingwen Liu, Weibin Liao, Xin Gao, Junfeng Zhao, Yasha Wang
arXiv:2610. 12768v1 Announce Type: cross Abstract: Semantic query engines evaluate natural-language filters with a large language model, and every evaluation is a costly oracle call.
By Oktie Hassanzadeh, Dharmashankar Subramanian
arXiv:2601.13111v3 Announce Type: replace-cross
Abstract: Realistic text-to-SQL workflows often require joining multiple tables. As a result, accurately retrieving the relevant set of tables becomes...
By Hassan Soliman, Vivek Gupta, Dan Roth, Iryna Gurevych
arXiv:2609.22259v1 Announce Type: new
Abstract: Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/wit...
By Qing Ye
arXiv:2606. 04646v1 Announce Type: cross Abstract: Many real-world questions over business, legal, and scientific corpora are natural-language versions of database-style queries over records latent in text.
By Mengao Zhang, Xiang Yang, Chang Liu, Tianhui Tan, Ke-wei Huang
arXiv:2607. 22639v1 Announce Type: new Abstract: Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via constrained beam search.
By Sai Shruthi Sistla, Ashutosh Hathidara, Christopher Toukmaji, Mayank Shrivastava, Karthikeyan Asokkumar
arXiv:2609.14652v1 Announce Type: cross
Abstract: Large Language Model (LLM) applications often transfer domain concepts into the model's context informally, through prompt prose, schema dumps, and e...
By Blake G. Fitch
The paper evaluates 17 paradigm-level configurations of in‑context learning (ICL) text‑to‑SQL pipelines across five common modules, measuring each module’s marginal accuracy contribution and cost for four different backbone models. It finds that execution‑feedback refinement consistently improves accuracy at low cost, while other modules only help under specific backbone conditions. The study also shows that investing in a more elaborate pipeline for a mid‑tier backbone can be more cost‑effective than upgrading to a high‑capability model with a lean pipeline, providing a tiered, cost‑aware guideline that generalizes to additional backbones.
By Jiayan Lin, Yujia Liu, Zijin Hong, Zheng Yuan, Yilin Xiao, Hao Chen, Qinggang Zhang, Xiao Huang, Feiran Huang