EnumGRPO is a self-improving optimizer for agentic query execution that reduces LLM-operator costs by ~317x while improving accuracy by 18% over a hybrid baseline across four databases.
CoRR abs/2408.00884(2024)
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
verdicts
UNVERDICTED 7representative citing papers
The authors define a taxonomy for LLM-enhanced relational operators categorized into Select, Match, Impute, Cluster and Order, and release LROBench to evaluate single and multi-operator queries on semantic database processing.
Larch uses a GNN-MDP formulation and a selectivity predictor plus dynamic programming to reorder semantic filter evaluation, cutting token usage 3x-19x versus prior systems on real and synthetic workloads.
AvalancheBench introduces a benchmark for data agents based on recovering a known latent world from observations, reporting that the best coding agent recovers only 26% on an e-commerce case.
SEMA-SQL automates natural language to efficient hybrid queries combining relational algebra with LLM semantic operations via a new Hybrid Relational Algebra abstraction.
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.
citing papers explorer
-
Cost-Aware Optimization for Agentic Query Execution
EnumGRPO is a self-improving optimizer for agentic query execution that reduces LLM-operator costs by ~317x while improving accuracy by 18% over a hybrid baseline across four databases.
-
Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis
The authors define a taxonomy for LLM-enhanced relational operators categorized into Select, Match, Impute, Cluster and Order, and release LROBench to evaluate single and multi-operator queries on semantic database processing.
-
Larch: Learned Query Optimization for Semantic Predicates
Larch uses a GNN-MDP formulation and a selectivity predictor plus dynamic programming to reorder semantic filter evaluation, cutting token usage 3x-19x versus prior systems on real and synthetic workloads.
-
AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery
AvalancheBench introduces a benchmark for data agents based on recovering a known latent world from observations, reporting that the best coding agent recovers only 26% on an e-commerce case.
-
SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models
SEMA-SQL automates natural language to efficient hybrid queries combining relational algebra with LLM semantic operations via a new Hybrid Relational Algebra abstraction.
-
Access Paths for Efficient Ordering with Large Language Models
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
-
Large Databases Need Small, Open-Weight Language Models
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.