mlsanityData to 7 Oct 2026

Towards Effective Orchestration of AI x DB Workloads

arXiv 2603.03772 ↗First posted 4 Mar 2026cs.DB cs.AIcited by 0

Not on the map. Why?

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

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 62 references that are in the map. First posted on arXiv 4 Mar 2026.

Builds on

21 of 62 references.

References · 21

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2024Llumnix: Dynamic Scheduling for Large Language Model Servingcited by 167
  5. 2018Rafiki: Machine Learning as an Analytics Service Systemcited by 33
  6. 2022End-to-end Optimization of Machine Learning Prediction Queriescited by 16
  7. 2019Extending Relational Query Processing with ML Inferencecited by 15
  8. 2015Frappe: Understanding the Usage and Perception of Mobile App Recommendations In-The-Wildcited by 14
  9. 2025Beyond Quacking: Deep Integration of Language Models and RAG into DuckDBcited by 12
  10. 2024SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligencecited by 11
  11. 2025Cortex AISQL: A Production SQL Engine for Unstructured Datacited by 11
  12. 2024Tally: Non-Intrusive Performance Isolation for Concurrent Deep Learning Workloadscited by 7
9 more
  1. 2025Batch Query Processing and Optimization for Agentic Workflowscited by 6
  2. 2025Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analyticscited by 6
  3. 2024Powering In-Database Dynamic Model Slicing for Structured Data Analyticscited by 5
  4. 2022The Tensor Data Platform: Towards an AI-centric Database Systemcited by 3
  5. 2025TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardwarecited by 3
  6. 2025Terabyte-Scale Analytics in the Blink of an Eyecited by 3
  7. 2025GRACEFUL: A Learned Cost Estimator For UDFscited by 2
  8. 2025Modeling Concurrency Control as a Learnable Functioncited by 1
  9. 2025Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysiscited by 1

Built on by

Not cited yet.