Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Shu, Ponnapalli, Soujanya, Shankar, Shreya, Zeighami, Sepanta, Zhu, Alan, Agarwal, Shubham, Chen, Ruiqi, Suwito, Samion, Yuan, Shuo, Stoica, Ion, Zaharia, Matei, Cheung, Alvin, Crooks, Natacha, Gonzalez, Joseph E., Parameswaran, Aditya G.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917130304225280
author Liu, Shu
Ponnapalli, Soujanya
Shankar, Shreya
Zeighami, Sepanta
Zhu, Alan
Agarwal, Shubham
Chen, Ruiqi
Suwito, Samion
Yuan, Shuo
Stoica, Ion
Zaharia, Matei
Cheung, Alvin
Crooks, Natacha
Gonzalez, Joseph E.
Parameswaran, Aditya G.
author_facet Liu, Shu
Ponnapalli, Soujanya
Shankar, Shreya
Zeighami, Sepanta
Zhu, Alan
Agarwal, Shubham
Chen, Ruiqi
Suwito, Samion
Yuan, Shuo
Stoica, Ion
Zaharia, Matei
Cheung, Alvin
Crooks, Natacha
Gonzalez, Joseph E.
Parameswaran, Aditya G.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00997
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
Liu, Shu
Ponnapalli, Soujanya
Shankar, Shreya
Zeighami, Sepanta
Zhu, Alan
Agarwal, Shubham
Chen, Ruiqi
Suwito, Samion
Yuan, Shuo
Stoica, Ion
Zaharia, Matei
Cheung, Alvin
Crooks, Natacha
Gonzalez, Joseph E.
Parameswaran, Aditya G.
Artificial Intelligence
Databases
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.
title Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
topic Artificial Intelligence
Databases
url https://arxiv.org/abs/2509.00997