AI News HubLIVE
原文

Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

A new arXiv paper proposes GEM (Governed Evolving Memory), reframing long-term AI agent memory as a new data-management workload with state-level operations to overcome four failure modes of current record-level systems.

Article intelligence

EngineersAdvanced

Key points

  • Current agent memory systems suffer from unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval
  • GEM replaces record-level database operations with four state-level operators: ingestion, revision, forgetting, and retrieval
  • The paper proves that no record-level system can satisfy the six correctness conditions
  • A prototype called MemState on a property-graph backend demonstrates feasibility

Why it matters

This matters because current agent memory systems suffer from unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26252] Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

[Submitted on 25 May 2026]

Title:Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

View a PDF of the paper titled Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory, by Abdelghny Orogat and Essam Mansour

View PDF HTML (experimental)

Abstract:Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as storage. They localize correctness at records, embeddings, or edges. Each supplies only some of the capabilities that long-term memory requires. The result is four recurring failure modes: unregulated growth, missing semantic revision, capacity-driven forgetting, and read-only retrieval. In our vision, long-term agent memory is a new data-management workload. Its correctness is a property of the state trajectory, not of individual records. We formalize this as Governed Evolving Memory (GEM). GEM replaces record-level database operations with four state-level operators: ingestion, revision, forgetting, and retrieval. Six correctness conditions govern how the state evolves. Three structural observations establish that no record-level system can satisfy these conditions, regardless of the storage model. We realize the abstraction in MemState, a prototype on a property-graph backend. MemState validates feasibility and exposes the gap to a native engine. We outline three research directions that define memory-centric data management as a workload.

Subjects:

Artificial Intelligence (cs.AI); Databases (cs.DB)

Cite as: arXiv:2605.26252 [cs.AI]

(or arXiv:2605.26252v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.26252

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Abdelghny Orogat [view email] [v1] Mon, 25 May 2026 18:22:42 UTC (801 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory, by Abdelghny Orogat and Essam Mansour

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs cs.DB

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)