Metraipolis › archive › dc_7f32d64d2b8f

Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL — arXiv:2608.15389

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15389
License (as archived)
CC0-1.0
Archived
2026-10-18T17:18:20.112Z
SHA-256 of the archived text
3726d870499b34796474c48d637af15bc876320ccbdbeee19d1eb312e3f37143
Stable URL of this page
https://metraipolis.com/documento/dc_7f32d64d2b8f

How to cite

Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL — arXiv:2608.15389 — arXiv (en), https://arxiv.org/abs/2608.15389 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f32d64d2b8f (Metraipolis archive dc_7f32d64d2b8f, sha256 3726d870499b34796474c48d637af15bc876320ccbdbeee19d1eb312e3f37143)
BibTeX
@misc{dc7f32d64d2b8f,
  title = {Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL — arXiv:2608.15389},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15389},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f32d64d2b8f; sha256 3726d870499b34796474c48d637af15bc876320ccbdbeee19d1eb312e3f37143},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15389. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15389 — 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 2026-10-18T16:29:13.796Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).