FERN ranks frozen retrievers for Text-to-SQL table retrieval
A LightGBM ranker over three frozen retrievers approaches RASL's published recall without generative LLM calls.
Stories per day · 30 days
3 RSS
Relatedbeaver1bird1cross-source-reasoning1deep-research-agents1enterprise-databases1graphrag1lightgbm1query-logs1qwen1reinforcement-learning1spider1table-retrieval1
8 stories, newest first · one card per story
Stories tagged #text-to-sql
Text-to-SQL framework learns database structure from query logs
On Beaver it reports 95.7% execution validity versus 60.8% for embedding retrieval, with experts preferring it 70% to 10%.
4B HybridResearcher beats larger Qwen model on cross-source research
It gains 30.0 pass@8 points over Qwen3.5-4B and 8.3 over Qwen3.5-397B-A17B on HybridDeepResearch.
ARCS: Towards Precise Text-to-SQL via Structured Disambiguation
ARCS benchmark shows text-to-SQL remains weak when natural question ambiguity is present.
FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs
FALCON generates realistic, ambiguity-aware NL2SQL training pairs with compact open models, matching or exceeding challenging benchmark complexity locally.
Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows
Argo-Bench tests data agents on 210 enterprise tasks over a 7.5-billion-row simulated warehouse.
Making Agents More Consistent: Skills Should Form Habits for Repeat Tasks
Paper proposes skill habit formation so agents cache deterministic skills from execution history, fixing 38-74% answer inconsistency and cutting tokens 14-56%.
MasterControl Seventeen Every Time
Governed enterprise analytics study shows deterministic policy execution matched 110/110 answer-and-evidence contracts while runtime agent planning matched none.