The Dynamic Gist-Based Memory Model (DGMM): A Memory-Centric Architecture for Artificial Intelligence

TL;DR

The paper introduces DGMM, a memory-centric AI architecture that explicitly represents experience as an evolving, graph-structured memory to improve interpretability, persistence, and temporal grounding.

Contribution

It proposes a novel memory model that treats experience as a structured, persistent graph, contrasting with traditional parameter-centric approaches.

Findings

DGMM encodes experience as interconnected conceptual structures.

Supports episodic persistence and cue-conditioned recall.

Enables interpretable, context-aware AI without retraining.

Abstract

Contemporary artificial intelligence systems achieve strong performance through large-scale parameterization, retrieval augmentation, and training on extensive static corpora. Despite these advances, they continue to face limitations in persistent memory, temporal grounding, provenance, and interpretability. These challenges are especially pronounced in large language models, where experience is encoded implicitly in fixed parameters, limiting the ability to preserve, inspect, and reinterpret past interactions over time. This paper establishes a memory-centric architectural foundation for artificial intelligence in which experience is represented explicitly and persistently to support temporal grounding, provenance, and interpretability. It proposes an alternative to parameter-centric approaches by treating memory as a first-class, structured substrate for reasoning. We introduce the Dynamic Gist-Based Memory Model (DGMM), an architecture in which experience is represented as an evolving, graph-structured episodic-semantic memory. DGMM encodes experience as interconnected conceptual structures grounded in time, source, and interaction context, and defines selective, cue-conditioned recall as the mechanism for constructing working memory. A formal schema and architectural invariants are provided based on additive memory growth and recall-conditioned interpretation. The results specify properties of DGMM, including episodic persistence, locality of cue-conditioned surprise, and contextual variability without structural modification of stored memory. DGMM provides a coherent architectural theory in which memory is explicit and persistent, supporting evolving interpretation without retraining and enabling interpretable, context-aware, and temporally grounded AI systems.