AI Briefing#text-to-sql
The latest AI and developer news about #text-to-sql, with the original source and a short summary.
The latest AI and developer news about #text-to-sql, with the original source and a short summary.
NVIDIA has released an open-source framework that automatically generates ontologies from DB metadata to validate AI agent SQL.
Migrated LangGraph workflows without rewriting to mitigate high-concurrency latency.
Validated complex query processing and a 60% reduction in response time by integrating LangGraph supervisor structure with AgentCore tools.
Reduced Text-to-SQL agent execution time by up to 5x and decreased tool calls from 8 to 1.
The ReViSQL-K2.6 model achieved human-level performance on Text-to-SQL benchmarks without scaffolding through RLVR and reward shaping.
LG AI Research announced ReSQL, which utilizes execution errors as learning signals to improve Text-to-SQL performance in lightweight models.
LG AI Research has released ReSQL, which recycles SQL errors from lightweight models for training to outperform GPT-4.
Cube announced a semantic layer integration with LangChain to enhance the accuracy of LLM-based applications.
feyn, the developer of Chonkie, has released the SQRL model series under Apache 2.0, which generates SQL after directly exploring the DB.
LG AI Research and KAIST took first place in the EHRSQL task at NAACL 2024 with a highly reliable Text-to-SQL model for extracting medical data.
LG AI Research, together with KAIST, took 1st place at the NAACL 2024 workshop with a reliable Text-to-SQL model that improves access to medical data.
Google has unveiled Gemini-SQL2, which achieved SOTA on the BIRD benchmark by leveraging Gemini 3.1 Pro.
Embedding past SQL with intent and structure produces more accurate Text-to-SQL.