Metraipolis › archive › dc_d263dcd84193

Reimagining Text-to-SQL: A Survey of Large Language Model Architectures and Strategies — arXiv:2611.00171

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.00171
License (as archived): CC0-1.0
Archived: 2026-11-03T18:11:50.171Z
SHA-256 of the archived text: 20c210f866f26943284b472d9df755965e65c7768f661d84996a77cf9c74f69c
Stable URL of this page: https://metraipolis.com/documento/dc_d263dcd84193

How to cite

Reimagining Text-to-SQL: A Survey of Large Language Model Architectures and Strategies — arXiv:2611.00171 — arXiv (en), https://arxiv.org/abs/2611.00171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d263dcd84193 (Metraipolis archive dc_d263dcd84193, sha256 20c210f866f26943284b472d9df755965e65c7768f661d84996a77cf9c74f69c)

BibTeX

@misc{dcd263dcd84193,
  title = {Reimagining Text-to-SQL: A Survey of Large Language Model Architectures and Strategies — arXiv:2611.00171},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00171},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d263dcd84193; sha256 20c210f866f26943284b472d9df755965e65c7768f661d84996a77cf9c74f69c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-SQL systems translate natural language questions into executable SQL queries, democratizing access to relational data. Early approaches relied on handcrafted rules and template matching, while subsequent neural methods introduced encoder-decoder architectures, schema linking, and constrained decoding to handle increasingly complex queries. The emergence of large language models (LLMs), exemplified by systems such as ReFoRCE, Agentar-Scale-SQL, Snowflake's Arctic-Text2SQL-R1, and the modular XiYan-SQL framework, has dramatically advanced the field, pushing execution accuracy to new state-of-the-art levels on challenging benchmarks such as Spider, Spider 2.0, and BIRD. In parallel, modular frameworks decompose the task into sub-problems (schema retrieval, sketch-based generation, repair, and ranking), while agentic systems coordinate multiple specialized agents that communicate and dynamically allocate sub-tasks. This survey systematically reviews these LLM-driven approaches within a unified taxonomy of five paradigms (in-context learning, supervised and parameter-efficient fine-tuning, agentic and tool-augmented orchestration, retrieval-augmented generation, and reinforcement learning) and characterizes them by model granularity (monolithic vs. modular), level of supervision (zero-shot, fine-tuned, or reinforcement-based), and reasoning style (direct decoding vs. decomposed multi-step reasoning). We further analyze evaluation metrics, datasets, and open challenges, including domain generalization, efficiency, and real-world deployment, and we examine the role of the semantic layer in production systems. As LLMs increasingly access sensitive databases, we also discuss responsible AI practices. We survey over 100 papers and technical resources, focusing on work published between 2022 and 2026.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00171 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:09:53.261Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).