cs.AIOct 30, 2026

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

Authors: Shikhar Dave, Bhaskarjit Sarmah, Stefano Pasquali

Organizations: Domyn, New Delhi, India · Domyn, New York, NY, United States

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

Figure 2: Evolution of Text-to-SQL benchmarks from 1990 to 2025. Each bubble represents a dataset positioned by its year of introduction (x-axis) and scale in NL–SQL pairs (y-axis, log scale), with color indicating dataset type. Background shading delineates three research eras: rule-based (pre-2016), neural (2016–2021), and LLM-driven (2021–present). Early benchmarks such as ATIS and GeoQuery were small and single-domain; the neural era introduced large-scale, cross-domain suites (WikiSQL, Spider, BIRD); and the LLM era has shifted focus toward enterprise-realistic (BEAVER, Spider 2.0) and contamination-free live evaluation (LiveSQLBench), prioritizing deployment fidelity over dataset scale alone.
Figure 3: Property coverage matrix for Text-to-SQL evaluation metrics. Each cell indicates whether a metric fully supports ( ∗* ), partially supports (o), or does not support (–) a given evaluation property. Execution Accuracy (EX) and Valid Efficiency Score (VES) require database access but capture semantic correctness, whereas structure-aware metrics such as SQAM and TSED provide partial credit and syntactic fidelity without requiring query execution, making them suitable for privacy-restricted or compliance-sensitive deployment settings. No single metric covers all properties, reinforcing the need for multi-metric evaluation protocols.
Figure 4: Comparison of reward strategies for Text-to-SQL on BIRD. Each bar shows the execution accuracy reported in the original paper, together with the model size and reward design. Values are taken as reported and mix BIRD development and test splits, so they indicate broad trends rather than a controlled comparison. Moving from supervised cross-entropy (62.0%) to composite and execution-grounded rewards (up to 73.5%) suggests that fine-grained or verifiable reward functions yield substantial gains over supervised training alone, even at comparable model scales.
Figure 5: Temporal progression of the best reported execution accuracy (EX) on the BIRD test set (June 2023–September 2025). Each marker denotes a representative system at its time of publication, color-coded by paradigm: in-context learning (ICL), fine-tuning (FT), agentic/multi-agent, and reinforcement learning (RL). The grey frontier traces the running maximum, and the dashed line marks human expert performance (92.96%). Over approximately two years, the best reported accuracy roughly doubled, from 40.1% to 81.7%, yet an 11-point gap to human performance persists on the official test set.
Figure 6: Three-tier semantic layer for Text-to-SQL systems. The middle tier mediates between the natural language interface and the physical database by encoding business logic, metadata, schema-to-business-term mappings, and access-control policies, thereby reducing schema ambiguity and enforcing governance constraints on generated SQL.
More in this topic

Text-to-SQL

Text-to-SQL translates natural-language questions into executable database queries, linking user intent to schemas, values, and SQL logic.

See all 183 papers

Explore similar work

CardsList

  1. Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning

    Jun 14, 2026Feng Lyu, Jinfeng Cen, Sijing Duan +4Execution-Guided Text-to-SQLSelf-Training for Language Models

    Central South University · Tsinghua University · Nanjing University +1

  2. LIMIT: Less Is More for Instruction Tuning in Text-to-SQL

    Sep 21, 2026Haoyuan Ma, Hengwei Liu, Linjuan Wu +2Text-to-SQLInstruction-Tuning Data Selection

    Zhejiang University

  3. AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

    Apr 8, 2026Minh Tam Pham, Trinh Pham, Tong Chen +3Text-to-SQLMulti-Agent LLM Systems

    Griffith University (Australia) · The University of Queensland (Australia)