arXiv Open Access 2026

A universal LLM Framework for General Query Refinements

Eldar Hacohen Yuval Moskovitch Amit Somech
Lihat Sumber

Abstrak

Numerous studies have explored the SQL query refinement problem, where the objective is to minimally modify an input query so that it satisfies a specified set of constraints. However, these works typically target restricted classes of queries or constraints. We present OmniTune, a general framework for refining arbitrary SQL queries using LLM-based optimization by prompting (OPRO). OmniTune employs a two-step OPRO scheme that explores promising refinement subspaces and samples candidates within them, supported by concise history and skyline summaries for effective feedback. Experiments on a comprehensive benchmark demonstrate that OmniTune handles both previously studied refinement tasks and more complex scenarios beyond the scope of existing solutions.

Topik & Kata Kunci

Penulis (3)

E

Eldar Hacohen

Y

Yuval Moskovitch

A

Amit Somech

Format Sitasi

Hacohen, E., Moskovitch, Y., Somech, A. (2026). A universal LLM Framework for General Query Refinements. https://arxiv.org/abs/2602.15681

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓