Tag
MaP-SQL enhances Text-to-SQL listwise selection without fine-tuning by employing structured memory retrieval and permutation-based ranking aggregation, outperforming state-of-the-art methods with reduced token usage.
This paper proposes SDAM, a memory-based framework for complex Text-to-SQL that uses structure-difference aware reasoning, contradiction-aware reflection, and schema-grounded memory evolution to improve SQL generation. Experiments show modest gains on BIRD-dev and Spider-test benchmarks.
CHS-SQL proposes a confidence-guided heuristic search schema linking process for text-to-SQL using small language models, achieving state-of-the-art results by balancing precision and recall in schema selection.
Chat2DB is a cross-platform database client supporting 30+ databases, enabling users to generate, explain, and optimize SQL using their own AI model.
GRID is a grammar-constrained decoding engine for enterprise SQL generation that uses LALR(1) parser state as a viable-prefix oracle to enforce syntactic validity, role-based access control, and per-schema policy, providing provable guarantees and near-constant per-token cost with a hash-chained audit trail.
This paper studies which signals best predict correctness in text-to-SQL for selective prediction. It finds that verification-based signals from LLM judges outperform black-box statistical signals like self-consistency, and that a two-provider ensemble achieves 0.82 AUROC with well-calibrated probabilities.
Proposes SAGE, a framework for autonomously uncovering latent failure patterns in LLM-based Text-to-SQL generation by generating vulnerability hypotheses and iteratively verifying them. Experiments show SAGE reveals significant model fragility and discovered patterns transfer across models, with preliminary fine-tuning showing promising remediation.
This paper presents a semantic-layer-mediated NL2SQL agent that decouples intent from physical execution by reasoning over a curated semantic model, achieving 94.15% execution accuracy on the Spider2-snow benchmark.
Soma-SQL proposes an autonomous method to resolve multi-source ambiguity in natural language to SQL translation using synthetic query logs and ambiguity-driven execution probing, achieving 13% improvement in execution accuracy over state-of-the-art baselines.
OpenAI's cookbook demonstrates an end-to-end AI-assisted database change workflow using the Agents SDK, covering impact analysis, SQL generation, validation, and evaluation.
Progress-SQL introduces a multi-turn reinforcement learning framework with progressive rewards for Text-to-SQL, using an Oracle-guided Diagnostic Tree to provide dense reward signals and improve SQL query generation on benchmarks like BIRD and Spider.
This paper presents AgentNLQ, a multi-agent system for natural language to SQL conversion that achieves 78.1% semantic accuracy on the BIRD benchmark through schema enrichment and a self-correcting orchestrator.
This paper introduces AIDA, an autonomous agent framework designed to transform fragmented enterprise data into actionable business insights by leveraging reinforcement learning and a proprietary Domain-Specific Language for SQL execution.
OpenAI details an internal AI data agent built on GPT-5, Codex, and their Evals/Embeddings APIs that lets employees query over 600 petabytes across 70k datasets using natural language. The tool reduces time-to-insight from days to minutes and is used across Engineering, Finance, Research, and Go-To-Market teams.
WrenAI is an open-source GenBI engine that enables AI agents to generate, deploy, and govern business intelligence dashboards from any database, grounded in an open context layer for trustworthy semantics and governance.