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.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.DB 4verdicts
UNVERDICTED 4representative citing papers
NeurBench is a benchmark suite that quantifies drift via a drift factor and generates data/workloads to evaluate learned database components under controllable drift scenarios.
HIRE is a hybrid learned index that achieves up to 41.7x higher throughput under mixed workloads and reduces tail latency by up to 98% compared to state-of-the-art learned and traditional indexes.
MountDB extends RocksDB with Memtable-level model reuse and a block-aware learned disk index, reporting up to 1.5X write and 2.1X read throughput over state-of-the-art on large-scale workloads.
citing papers explorer
-
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.
-
NeurBench: A Benchmark Suite for Learned Database Components with Drift Modeling
NeurBench is a benchmark suite that quantifies drift via a drift factor and generates data/workloads to evaluate learned database components under controllable drift scenarios.
-
HIRE: A Hybrid Learned Index for Robust and Efficient Performance under Mixed Workloads
HIRE is a hybrid learned index that achieves up to 41.7x higher throughput under mixed workloads and reduces tail latency by up to 98% compared to state-of-the-art learned and traditional indexes.
-
A Pragmatic Approach to Learned Indexing in RocksDB: Targeted Optimizations with Minimal System Modification
MountDB extends RocksDB with Memtable-level model reuse and a block-aware learned disk index, reporting up to 1.5X write and 2.1X read throughput over state-of-the-art on large-scale workloads.