EUVIMEDEUVIMED entdecken
Crossref

AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale

Ziyang Wang, Yuanlei Zheng, Zhenbiao Cao, Xiaojin Zhang, Zhongyu Wei, Pei Fu, Zhenbo Luo, Wei Chen, Xiang Bai

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 33809-33817

DOI: 10.1609/aaai.v40i40.40672 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ziyang Wang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For industrial-scale text-to-SQL, supplying the entire database schema to Large Language Models (LLMs) is impractical due to context window limits and irrelevant noise. Schema linking, which filters the schema to a relevant subset, is therefore critical. However, existing methods incur prohibitive costs, struggle to trade off recall and noise, and scale poorly to large databases. We present AutoLink, an autonomous agent framework that reformulates schema linking as an iterative, agent-driven process. Guided by an LLM, AutoLink dynamically explores and expands the linked schema subset, progressively identifying necessary schema components without inputting the full database schema. Our experiments demonstrate AutoLink's superior performance, achieving state-of-the-art strict schema linking recall of 97.4% on Bird-Dev and 91.2% on Spider 2.0-Lite, with competitive execution accuracy, i.e., 68.7% EX on Bird-Dev (better than CHESS) and 34.9% EX on Spider 2.0-Lite (ranking 2nd on the official leaderboard). Crucially, AutoLink exhibits exceptional scalability, maintaining high recall, efficient token consumption, and robust execution accuracy on large schemas (e.g., over 3,000 columns) where existing methods severely degrade—making it a highly scalable, high-recall schema-linking solution for industrial text-to-SQL systems.

Zitieren

APA

Wang, Z., Zheng, Y., Cao, Z., Zhang, X., Wei, Z., Fu, P., Luo, Z., Chen, W., & Bai, X. (2026). AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 33809-33817. https://doi.org/10.1609/aaai.v40i40.40672

Vancouver

Wang Z, Zheng Y, Cao Z, Zhang X, Wei Z, Fu P, et al. AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):33809-33817. doi:10.1609/aaai.v40i40.40672

BibTeX
@article{Wang2026,
  author = {Wang, Ziyang and Zheng, Yuanlei and Cao, Zhenbiao and Zhang, Xiaojin and Wei, Zhongyu and Fu, Pei and Luo, Zhenbo and Chen, Wei and Bai, Xiang},
  title = {AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {40},
  pages = {33809--33817},
  doi = {10.1609/aaai.v40i40.40672}
}
Kostenlos starten →