Query-centric AQP and proxy-model strategies reduce expensive model calls by 60-90% with under 10% error on TPC-DS and LLM tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models
Query-centric AQP and proxy-model strategies reduce expensive model calls by 60-90% with under 10% error on TPC-DS and LLM tasks.