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

arXiv: https://arxiv.org/abs/2509.00997 · HTML: https://mlsanity.com/paper/2509.00997/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 2 of its 21 references that are in the map.
- First posted on arXiv 31 Aug 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 2 of 2)

- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [OrpheusDB: Bolt-on Versioning for Relational Databases](https://mlsanity.com/paper/1703.02475/) (2017)

## Built on by (most cited first, 30 of 32)

- [Barbarians at the Gate: How AI is Upending Systems Research](https://mlsanity.com/paper/2510.06189/) (2025)
- [Are We Ready For An Agent-Native Memory System?](https://mlsanity.com/paper/2606.24775/) (2026)
- [AgentSM: Semantic Memory for Agentic Text-to-SQL](https://mlsanity.com/paper/2601.15709/) (2026)
- [Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective](https://mlsanity.com/paper/2603.16104/) (2026)
- [TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory](https://mlsanity.com/paper/2606.06240/) (2026)
- [Arming Data Agents with Tribal Knowledge](https://mlsanity.com/paper/2602.13521/) (2026)
- [AgenticDataBench: A Comprehensive Benchmark for Data Agents](https://mlsanity.com/paper/2607.01647/) (2026)
- [Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehouse](https://mlsanity.com/paper/2510.09567/) (2025)
- [Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governance](https://mlsanity.com/paper/2511.16402/) (2025)
- [Supporting Dynamic Agentic Workloads: How Data and Agents Interact](https://mlsanity.com/paper/2512.09548/) (2025)
- [Let the Barbarians In: How AI Can Accelerate Systems Performance Research](https://mlsanity.com/paper/2512.14806/) (2025)
- [ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization](https://mlsanity.com/paper/2602.02597/) (2026)
- [Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?](https://mlsanity.com/paper/2602.21480/) (2026)
- [stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://mlsanity.com/paper/2603.03589/) (2026)
- ["Skill Issues'': Data-Centric Optimization of Lakehouse Agents](https://mlsanity.com/paper/2606.01185/) (2026)
- [Querying Everything Everywhere All at Once: Supervaluationism for the Agentic Lakehouse](https://mlsanity.com/paper/2603.13380/) (2026)
- [AgileLog: A Forkable Shared Log for Agents on Data Streams](https://mlsanity.com/paper/2604.14590/) (2026)
- [Declarative Data Services: Structured Agentic Discovery for Composing Data Systems](https://mlsanity.com/paper/2605.20690/) (2026)
- [A Query Engine for the Agents](https://mlsanity.com/paper/2605.27785/) (2026)
- [Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation](https://mlsanity.com/paper/2605.30862/) (2026)
- [Data Flow Control: Data Safety Policies for AI Agents](https://mlsanity.com/paper/2606.05679/) (2026)
- [SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering](https://mlsanity.com/paper/2607.00151/) (2026)
- [GitLake: Git-for-data for the agentic lakehouse](https://mlsanity.com/paper/2607.08319/) (2026)
- [Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]](https://mlsanity.com/paper/2607.10508/) (2026)
- [Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap](https://mlsanity.com/paper/2607.12113/) (2026)
- [KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planning](https://mlsanity.com/paper/2608.06530/) (2026)
- [Git4Data: Database-Native Version Control for AI Agents](https://mlsanity.com/paper/2609.02106/) (2026)
- [Efficiently Linking Unstructured Data for Multi-step Reasoning](https://mlsanity.com/paper/2609.19491/) (2026)
- [Towards an AI Software Factory for Data Systems](https://mlsanity.com/paper/2609.36323/) (2026)
- [Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows](https://mlsanity.com/paper/2610.02122/) (2026)

## Abstract (arXiv)

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.