2 papers
cs.MA2025
Supporting Dynamic Agentic Workloads: How Data and Agents Interact
Ioana Giurgiu, Michael E. Nidd
The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. T…
cs.DB2025
Bootstrapping Learned Cost Models with Synthetic SQL Queries
Michael Nidd, Christoph Miksovic, Thomas Gschwind +3
Having access to realistic workloads for a given database instance is extremely important to enable stress and vulnerability testing, as well as to optimize for cost and performanc…