CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query Processing

2026-06-27

AI Summary

This work addresses the challenge that existing semantic query optimizers struggle to integrate intermediate outputs of semantic operators into relational optimization frameworks, thereby failing to jointly optimize quality, latency, and cost. To overcome this limitation, the authors propose Task-extended Relational Algebra (TxRA), which compiles natural language intents into a task-oriented directed acyclic graph (DAG) plan space. TxRA enables joint optimization through structural rewriting, semantics-guided alternative plan generation, task-specific operators, and heterogeneous backend routing. A Bayesian optimization strategy is employed to select the optimal executable plan under user-specified trade-off constraints. Experiments on SemBench demonstrate that, compared to state-of-the-art approaches, the proposed method achieves an average per-scenario quality improvement of 0.49 while reducing latency and cost by factors of 165.7× and 310.3×, respectively.

Abstract

Semantic query processing engines (SQPEs) extend relational query processing with semantic operators that are executed via model inference over unstructured data. Optimizing such queries is inherently multi-objective: model inference dominates latency and monetary cost, and outputs are stochastic and backend-dependent, so quality must be optimized alongside efficiency. Existing SQPE optimizers do not expose each semantic operator instance's intermediate task outputs as a relational optimization object, leaving optimization unable to filter, reorder, route, threshold, or jointly tune them. We present CADENZA, which compiles each semantic operator instance--a template bound to a natural-language intent--into an intent-specific plan space of typed task DAGs and selects an executable plan under user-specified quality-latency-cost trade-offs. CADENZA introduces task-extended relational algebra (TxRA), a conservative extension of relational algebra with task-specific operators. The logical planner synthesizes seed TxRA plans, applies structural rewrites whose safety conditions are checked from operator dependencies, and enumerates semantics-guided alternatives from alternative-generation templates. The physical planner compiles each task-specific operator into a router over heterogeneous backends and jointly tunes routing cutpoints, backend parameters, and relational thresholds with Bayesian optimization. On SemBench, CADENZA improves the scenario-level averages of quality, latency, and cost by up to +0.49, 165.7x, and 310.3x, respectively, relative to state-of-the-art.

Problem

• semantic query processing
• multi-objective optimization
• semantic operators
• intermediate task outputs
• quality-latency-cost trade-offs

Innovation

• task-specific operator DAGs
• task-extended relational algebra
• semantic query optimization
• Bayesian optimization
• heterogeneous backend routing