mlsanityData to 7 Oct 2026

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

arXiv 2509.00997 ↗First posted 31 Aug 2025cs.AI cs.DBcited by 30

On the map: LLM agents and tool use → Web, search, and research agents

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.

Key facts. Cited by 30 papers in the map (data through 7 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.

Builds on

2 of 21 references.

References · 2

  1. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  2. 2017OrpheusDB: Bolt-on Versioning for Relational Databasescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 25.

30 papers.

Sort:

By area:

  1. 2025Barbarians at the Gate: How AI is Upending Systems Researchcited by 48
  2. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
  3. 2026Are We Ready For An Agent-Native Memory System?cited by 11
  4. 2026Efficient LLM Serving for Agentic Workflows: A Data Systems Perspectivecited by 10
  5. 2026TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memorycited by 7
  6. 2025Safe, Untrusted, "Proof-Carrying" AI Agents: toward the agentic lakehousecited by 6
  7. 2026Arming Data Agents with Tribal Knowledgecited by 6
  8. 2025Trustworthy AI in the Agentic Lakehouse: from Concurrency to Governancecited by 5
  9. 2026AgenticDataBench: A Comprehensive Benchmark for Data Agentscited by 5
  10. 2025Supporting Dynamic Agentic Workloads: How Data and Agents Interactcited by 2
  11. 2025Let the Barbarians In: How AI Can Accelerate Systems Performance Researchcited by 2
  12. 2026ContextEvolve: Multi-Agent Context Compression for Systems Code Optimizationcited by 2
18 more
  1. 2026Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?cited by 1
  2. 2026"Skill Issues'': Data-Centric Optimization of Lakehouse Agentscited by 1
  3. 2026stratum: A System Infrastructure for Massive Agent-Centric ML Workloadscited by 0
  4. 2026Querying Everything Everywhere All at Once: Supervaluationism for the Agentic Lakehousecited by 0
  5. 2026AgileLog: A Forkable Shared Log for Agents on Data Streamscited by 0
  6. 2026Declarative Data Services: Structured Agentic Discovery for Composing Data Systemscited by 0
  7. 2026A Query Engine for the Agentscited by 0
  8. 2026Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderationcited by 0
  9. 2026Data Flow Control: Data Safety Policies for AI Agentscited by 0
  10. 2026SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineeringcited by 0
  11. 2026GitLake: Git-for-data for the agentic lakehousecited by 0
  12. 2026Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful, Transparent, and Collaborative Research [Vision]cited by 0
  13. 2026Toward Trustworthy Autonomous Science: A Two-Year Community Roadmapcited by 0
  14. 2026KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planningcited by 0
  15. 2026Git4Data: Database-Native Version Control for AI Agentscited by 0
  16. 2026Efficiently Linking Unstructured Data for Multi-step Reasoningcited by 0
  17. 2026Towards an AI Software Factory for Data Systemscited by 0
  18. 2026Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Data Agents: Agentic Data Systems
  2. 2025Large Language Model-based Data Science Agent: A Survey
  3. 2025Rethinking Query Optimization for Multi-Agent Systems [Vision]
  4. 2026Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
  5. 2025A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
  6. 2025Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems
  7. 2026Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
  8. 2025LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions