LLM-assisted synthesis of database storage readers that bypass engines and materialize PostgreSQL/MySQL data as Apache Arrow for analytical engines.
Bespoke OLAP: Synthesizing workload-specific one-size-fits-one database engines
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
LLM-synthesized GPU query kernels outperform engineered engines by 7.4x, but a portable SYCL engine with lifted optimizations closes the gap to 1.27x, suggesting engineering remains preferable on GPUs.
Agent-driven code synthesis produces workload-specialized cardinality estimators that cut PostgreSQL runtime 33% on JOB and 68% on JOB-Complex while lowering median q-error from 190.5 to 11.5.
Jitskit is an iterative LLM-based synthesis pipeline that generates key-value stores matching spec cards for YCSB workloads, resources, and properties, outperforming SOTA baselines on all 18 tested cases by up to 4.6x.
SpecDB generates a 23,779-line Rust database via LLM subagents that matches PostgreSQL and MySQL tpmC on TPC-C while using roughly 3% of their code size.
FM-Agent automates top-down natural-language Hoare reasoning with LLMs and reports 522 new bugs in large, previously tested systems up to 143k LoC.
citing papers explorer
-
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass
LLM-assisted synthesis of database storage readers that bypass engines and materialize PostgreSQL/MySQL data as Apache Arrow for analytical engines.
-
From Custom-Fit to Portable: Bridging the Gap Between Synthesized and Engineered GPU Query Execution
LLM-synthesized GPU query kernels outperform engineered engines by 7.4x, but a portable SYCL engine with lifted optimizations closes the gap to 1.27x, suggesting engineering remains preferable on GPUs.
-
Bespoke-Card: Why Tune When You Can Generate? Synthesizing Workload-Specific Cardinality Estimators
Agent-driven code synthesis produces workload-specialized cardinality estimators that cut PostgreSQL runtime 33% on JOB and 68% on JOB-Complex while lowering median q-error from 190.5 to 11.5.
-
The Time is Here for Just-in-Time Systems: Challenges and Opportunities
Jitskit is an iterative LLM-based synthesis pipeline that generates key-value stores matching spec cards for YCSB workloads, resources, and properties, outperforming SOTA baselines on all 18 tested cases by up to 4.6x.
-
SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition
SpecDB generates a 23,779-line Rust database via LLM subagents that matches PostgreSQL and MySQL tpmC on TPC-C while using roughly 3% of their code size.
-
FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning
FM-Agent automates top-down natural-language Hoare reasoning with LLMs and reports 522 new bugs in large, previously tested systems up to 143k LoC.
- Tailwind: A Practical Framework for Query Accelerators