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.
Abadi, Samuel Madden, and Nabil Hachem
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.DB 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
In closed-loop OLTP the group commit timer collapses to greedy above λ*=2/F0, rendering tuning vacuous and the greedy policy within 0.1% of oracle optimum.
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.
-
Group Commit Self-Clocks: Why Tuning Is Unnecessary Above a Device-Set Load Threshold
In closed-loop OLTP the group commit timer collapses to greedy above λ*=2/F0, rendering tuning vacuous and the greedy policy within 0.1% of oracle optimum.