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

arXiv: https://arxiv.org/abs/2605.02106 · HTML: https://mlsanity.com/paper/2605.02106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 58 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Continual Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2402.01364/) (2024)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [Larimar: Large Language Models with Episodic Memory Control](https://mlsanity.com/paper/2403.11901/) (2024)
- [ChronoR: Rotation Based Temporal Knowledge Graph Embedding](https://mlsanity.com/paper/2103.10379/) (2021)
- [Time is Encoded in the Weights of Finetuned Language Models](https://mlsanity.com/paper/2312.13401/) (2023)
- [Local Interpretations for Explainable Natural Language Processing: A Survey](https://mlsanity.com/paper/2103.11072/) (2021)
- [A Survey on Temporal Knowledge Graph: Representation Learning and Applications](https://mlsanity.com/paper/2403.04782/) (2024)
- [Set the Clock: Temporal Alignment of Pretrained Language Models](https://mlsanity.com/paper/2402.16797/) (2024)
- [Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection](https://mlsanity.com/paper/2204.07275/) (2022)
- [A model of semantic completion in generative episodic memory](https://mlsanity.com/paper/2111.13537/) (2021)
- [TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs](https://mlsanity.com/paper/2501.04343/) (2025)
- [Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation](https://mlsanity.com/paper/2506.05939/) (2025)
- [GENESIS: A Generative Model of Episodic-Semantic Interaction](https://mlsanity.com/paper/2510.15828/) (2025)

## Abstract (arXiv)

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.