Saved in:
Bibliographic Details
Main Author: Logan, Joe
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.09913
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909990860619776
author Logan, Joe
author_facet Logan, Joe
contents Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval is read-only, and temporal continuity is absent. We define the \textit{Continuum Memory Architecture} (CMA), a class of systems that maintain and update internal state across interactions through persistent storage, selective retention, associative routing, temporal chaining, and consolidation into higher-order abstractions. Rather than disclosing implementation specifics, we specify the architectural requirements CMA imposes and show consistent behavioral advantages on tasks that expose RAG's structural inability to accumulate, mutate, or disambiguate memory. The empirical probes (knowledge updates, temporal association, associative recall, contextual disambiguation) demonstrate that CMA is a necessary architectural primitive for long-horizon agents while highlighting open challenges around latency, drift, and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09913
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Continuum Memory Architectures for Long-Horizon LLM Agents
Logan, Joe
Artificial Intelligence
Information Retrieval
Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval is read-only, and temporal continuity is absent. We define the \textit{Continuum Memory Architecture} (CMA), a class of systems that maintain and update internal state across interactions through persistent storage, selective retention, associative routing, temporal chaining, and consolidation into higher-order abstractions. Rather than disclosing implementation specifics, we specify the architectural requirements CMA imposes and show consistent behavioral advantages on tasks that expose RAG's structural inability to accumulate, mutate, or disambiguate memory. The empirical probes (knowledge updates, temporal association, associative recall, contextual disambiguation) demonstrate that CMA is a necessary architectural primitive for long-horizon agents while highlighting open challenges around latency, drift, and interpretability.
title Continuum Memory Architectures for Long-Horizon LLM Agents
topic Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2601.09913