Continuum Memory Architectures for Long-Horizon LLM Agents

TL;DR

The paper introduces the Continuum Memory Architecture (CMA), a novel system for LLM agents that maintains and updates internal memory over time, enabling better long-term knowledge management and contextual reasoning.

Contribution

It defines the architectural requirements for CMA, demonstrating its advantages over retrieval-augmented generation in tasks requiring memory accumulation and disambiguation.

Findings

CMA improves long-term knowledge retention in LLM agents.

CMA enables effective temporal association and contextual disambiguation.

Empirical results show CMA's necessity for long-horizon reasoning.

Abstract

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.