SOURCE-LINKED INTELLIGENCE

Compositional Online Learning for Semantic Data Processing Systems

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

An LLM call in a semantic data processing system is expensive enough to dominate query cost, yet slow enough to hide a CPU-side learner's update behind its round-trip. In production, LLM compute accounts for $80-90\%$ of query cost, and each call costs $10^5-10^7\times$ a relational predicate. The latency window inverts a design constraint of classical adaptive query processing, where online learners had to stay lightweight to avoid dominating the predicates they optimize. At LLM latency, per-call gradient steps and per-batch threshold solves fit inside the round-trip. We develop compositional

Read original source ↗ Open in workspace

recordType

paper

region

Global