Highlight

Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents

A survey on persistent memory, state, and governance in LLMAgents.

Based on

Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents

arxiv.org
Read original article →

The paper surveys the literature on always-on agents, which are systems whose future behavior depends on durable state accumulated across earlier interactions.

It introduces a framework for evaluating these systems and connects them to databases, distributed systems, formal methods, capability security, and machine unlearning. The survey focuses on six diagnostic axes: authority, scope, mutability, provenance, recoverability, and actionability.

Abstract

The paper surveys the literature on always-on agents, which are systems whose future behavior depends on durable state accumulated across earlier interactions. It introduces a framework for evaluating these systems and connects them to databases, distributed systems, formal methods, capability security, and machine unlearning. The survey focuses on six diagnostic axes: authority, scope, mutability, provenance, recoverability, and actionability.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

persistent memorystate governanceLLMAgentsalways-on agentsAI AgentsLarge Language ModelsAgent MemoryData Governance
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources