Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
By: Shu Liu , Soujanya Ponnapalli , Shreya Shankar and more
Potential Business Impact:
Helps computers explore and solve data problems faster.
Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of exploration and solution formulation for the given task, one we call agentic speculation. The sheer volume and inefficiencies of agentic speculation can pose challenges for present-day data systems. We argue that data systems need to adapt to more natively support agentic workloads. We take advantage of the characteristics of agentic speculation that we identify, i.e., scale, heterogeneity, redundancy, and steerability - to outline a number of new research opportunities for a new agent-first data systems architecture, ranging from new query interfaces, to new query processing techniques, to new agentic memory stores.
Similar Papers
Supporting Dynamic Agentic Workloads: How Data and Agents Interact
Multiagent Systems
Helps AI teams share information faster and smarter.
Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems
Databases
Lets computers build smart data plans alone.
A Survey on Large Language Model-based Agents for Statistics and Data Science
Artificial Intelligence
Helps computers analyze data without experts.