Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
Summary: LLM agents to become dominant data workload; "agentic speculation"—high-throughput exploratory/solution iterations—creates scale, heterogeneity, redundancy, and steerability challenges. Proposes an agent-first DB architecture and research agenda (interfaces, processing, agentic memory) to natively support them. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Shu Liu (University of California Berkeley)
- 2. Soujanya Ponnapalli (University of California Berkeley)
- 3. Shreya Shankar (University of California Berkeley)
- 4. Sepanta Zeighami (University of California Berkeley)
- 5. Alan Zhu (University of California Berkeley)
- 6. Shubham Agarwal (University of California Berkeley)
- 7. Ruiqi Chen (University of California Berkeley)
- 8. Samion Suwito (University of California Berkeley)
- 9. Shuo Yuan (University of California Berkeley)
- 10. Ion Stoica (University of California Berkeley)
- 11. Matei Zaharia (University of California Berkeley)
- 12. Alvin Cheung (University of California Berkeley)
- 13. Natacha Crooks (University of California Berkeley)
- 14. Joseph E. Gonzalez (University of California Berkeley)
- 15. Aditya G. Parameswaran (University of California Berkeley)
BibTeX Citation
@inproceedings{liu_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Liu, Shu and Ponnapalli, Soujanya and Shankar, Shreya and Zeighami, Sepanta and Zhu, Alan and Agarwal, Shubham and Chen, Ruiqi and Suwito, Samion and Yuan, Shuo and Stoica, Ion and Zaharia, Matei and Cheung, Alvin and Crooks, Natacha and Gonzalez, Joseph E. and Parameswaran, Aditya G.},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,228 | Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 13,343 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 2 | 3,536 | How Large Language Models Will Disrupt Data Management | 2023 | VLDB |
| 3 | 5,978 | From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive Systems | 2019 | SIGMOD |
| 4 | 10,116 | Please Don't Kill My Vibe: Empowering Agents with Data Flow Control | 2026 | CIDR |
| 5 | 10,190 | AgenticScholar: Agentic Data Management with Pipeline Orchestration for Scholarly Corpora | 2026 | SIGMOD |
| 6 | 6,101 | LLM for Data Management | 2024 | VLDB |
| 7 | 13,375 | Reimagining Deep Learning Systems Through the Lens of Data Systems | 2024 | VLDB |
| 8 | 10,125 | A Vision for Autonomous Data Agent Collaboration: From Query-by-Integration to Query-by-Collaboration | 2026 | CIDR |
| 9 | 10,228 | Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective | 2026 | SIGMOD |
| 10 | 9,293 | Intelligent Agents for Data Exploration | 2024 | VLDB |