ATLAS: Adaptive Text-to-SQL with Lifecycle-Aware Self-Maintaining Context

Qing Zhang Shi-Jing Hu Zhi-Hui Lu

Aug 2026 · Proceedings of the VLDB Endowment · Vol 19, pp. 4838-4841 · 0 citations · 13 references

TL;DR

ATLAS addresses Text-to-SQL in production problems by co-locating schema metadata, semantic annotations, and vector embeddings entirely within a single RDBMS with native vector-index support.

Abstract

Deploying Text-to-SQL in production is hampered by context-window limits on large schemas, metadata that goes stale as schemas evolve, and infrastructure sprawl from external vector stores. We demonstrate ATLAS , which addresses all three by co-locating schema metadata, semantic annotations, and vector embeddings entirely within a single RDBMS with native vector-index support. ATLAS contributes: (1) Unified in-database storage with native vector indexes, requiring no external engine; (2) Two-stage adaptive schema linking that uses vector retrieval to narrow hundreds of tables to a compact candidate set before LLM refinement; (3) Rich Context life-cycle that automatically generates semantic descriptions, synonyms, sample values, business rules, and value mappings, bridging raw schema and LLM understanding; (4) Agent-driven self-maintenance via a coordinator-executor loop that detects DDL changes and regenerates annotations without manual intervention. We showcase three live scenarios on an enterprise database with 517 tables.

DOI Semantic Scholar

View source

Similar papers

#natural language process... Preprint Oct 2026

AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving Migration

A conversion pipeline is proposed, driven by coding agents with human-in-the-loop verification, that designs each document schema from expected access patterns and rewrites queries to be MongoDB-native, and builds an access-pattern-based text-to-MQL benchmark (AptMQL-Bench).

Hy Nguyen, Nabi Rezvani, Robin Vujanic · 0 citations

ExpeSQL: An Efficient, Experience-Guided Decompositional Search Framework for Text-to-SQL

This work introduces ExpeSQL, a zero-shot, open-source–compatible, and efficient framework that combines divide-and-conquer reasoning, Best-of-N candidate selection, and self-critique with experience-guided refinement that establishes a new paradigm for deployable, self-improving Text-to-SQL systems in dynamic, real-wo...

Unknown authors · 0 citations

SafeQL: Search-based Refinement for Safe and E � icient LLM-based Text-to-SQL

Geonho Lee, Min-Soo Kim · 0 citations

#artificial intelligence Preprint Sep 2026

A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark

A cost-aware single- generation agentic architecture whose schema- selection, metadata-retrieval, and error-repair components are designed for the requirements this regime imposes, and is competitive with leading systems at a single-generation operating point.

Yoga Sri Varshan Varadharajan, Ajay Yadav, Ritesh Goru et al. · 0 citations

Open access May 2026

SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL

SafeQL is proposed, a search-based refinement paradigm that redefines the role of the DBMS as an active guide in the refinement process, and significantly improves execution accuracy and efficiency compared to regeneration-based methods.

Geonho Lee, Min-Soo Kim · Proceedings of the VLDB Endo... · 0 citations

2026

LLCE-SQL: Data-Efficient Text-to-SQL Training via Logic-Linking Driven Collaborative Evolution

Training high-performance Text-to-SQL models typically requires massive synthetic datasets, yet existing augmentation methods suffer from semantic drift, structural homogenization, and limited complexity coverage, leading to diminishing returns at scale. This paper proposes LLCE-SQL, a Logic-Linking driven Collaborativ...

Yan Zhang, Jin Qi, Wei Xu et al. · IEEE Transactions on Audio,... · 0 citations