# Towards Effective Orchestration of AI x DB Workloads

arXiv: https://arxiv.org/abs/2603.03772 · HTML: https://mlsanity.com/paper/2603.03772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 62 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Rafiki: Machine Learning as an Analytics Service System](https://mlsanity.com/paper/1804.06087/) (2018)
- [End-to-end Optimization of Machine Learning Prediction Queries](https://mlsanity.com/paper/2206.00136/) (2022)
- [Extending Relational Query Processing with ML Inference](https://mlsanity.com/paper/1911.00231/) (2019)
- [Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB](https://mlsanity.com/paper/2504.01157/) (2025)
- [Frappe: Understanding the Usage and Perception of Mobile App Recommendations In-The-Wild](https://mlsanity.com/paper/1505.03014/) (2015)
- [SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence](https://mlsanity.com/paper/2411.06102/) (2024)
- [Cortex AISQL: A Production SQL Engine for Unstructured Data](https://mlsanity.com/paper/2511.07663/) (2025)
- [Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloads](https://mlsanity.com/paper/2410.07381/) (2024)
- [Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics](https://mlsanity.com/paper/2509.02751/) (2025)
- [Batch Query Processing and Optimization for Agentic Workflows](https://mlsanity.com/paper/2509.02121/) (2025)
- [Powering In-Database Dynamic Model Slicing for Structured Data Analytics](https://mlsanity.com/paper/2405.00568/) (2024)
- [The Tensor Data Platform: Towards an AI-centric Database System](https://mlsanity.com/paper/2211.02753/) (2022)
- [TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware](https://mlsanity.com/paper/2502.02818/) (2025)
- [Terabyte-Scale Analytics in the Blink of an Eye](https://mlsanity.com/paper/2506.09226/) (2025)
- [GRACEFUL: A Learned Cost Estimator For UDFs](https://mlsanity.com/paper/2503.23863/) (2025)
- [Modeling Concurrency Control as a Learnable Function](https://mlsanity.com/paper/2503.10036/) (2025)
- [Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis](https://mlsanity.com/paper/2510.12642/) (2025)

## Abstract (arXiv)

AI-driven analytics are increasingly crucial to data-centric decision-making. Executing relational and AI operators in separate runtimes prevents the database optimizer and runtime from coordinating operator ordering, model placement, batching, and state reuse. Integrating AI operators into database engines enables such coordination but raises challenges in jointly optimizing query processing and model execution, scheduling under resource contention, and reusing relational intermediates and AI artifacts. This paper formalizes AIxDB workloads as iterative, concurrent, and shareable executions that interleave relational and AI operators. We then advocate database-native orchestration as a paradigm for redesigning database engines for these workloads and distill two design principles: holistic AIxDB co-optimization and unified AIxDB cache management. We present NeurEngine as a proof-of-concept prototype and report preliminary results illustrating the performance benefits of database-native orchestration