New Text-to-Big SQL metrics show that LLM agents must balance accuracy with cost and speed at scale, where GPT-4o trades some accuracy for up to 12x speedup and GPT-5.2 proves more cost-effective than Gemini 3 Pro on large inputs.
Lero: A Learning-to-Rank Query Optimizer
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
StructuredSemanticSearch uses table discovery operators and orientation-aware integration on model-card tables to improve evidence coverage and diversity in model recommendation queries over a semantic baseline.
Co-evolving LLM-generated solutions with their evaluators enables discovery of novel database algorithms that outperform state-of-the-art baselines, including a query rewrite policy with up to 6.8x lower latency.
Proposes a formal DP-compatible framework with three unfairness measures (mutual information with TV proxy, MaxSAT-based repair, top-k tuple contribution) that satisfy positivity, monotonicity, and computability.
RELOAD achieves up to 2.4x higher robustness and 3.1x greater efficiency than prior RL-based query optimizers on Join Order Benchmark, TPC-DS, and Star Schema Benchmark.
citing papers explorer
-
Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?
New Text-to-Big SQL metrics show that LLM agents must balance accuracy with cost and speed at scale, where GPT-4o trades some accuracy for up to 12x speedup and GPT-5.2 proves more cost-effective than Gemini 3 Pro on large inputs.
-
Diversed Model Discovery via Structured Table Discovery
StructuredSemanticSearch uses table discovery operators and orientation-aware integration on model-card tables to improve evidence coverage and diversity in model recommendation queries over a semantic baseline.
-
AI-Driven Research for Databases
Co-evolving LLM-generated solutions with their evaluators enables discovery of novel database algorithms that outperform state-of-the-art baselines, including a query rewrite policy with up to 6.8x lower latency.
-
Measuring Database Unfairness via Dependency Quantification Under Differential Privacy
Proposes a formal DP-compatible framework with three unfairness measures (mutual information with TV proxy, MaxSAT-based repair, top-k tuple contribution) that satisfy positivity, monotonicity, and computability.
-
RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems
RELOAD achieves up to 2.4x higher robustness and 3.1x greater efficiency than prior RL-based query optimizers on Join Order Benchmark, TPC-DS, and Star Schema Benchmark.