mlsanityData to 7 Oct 2026

DYNA : Dynamic Episodic Memory Networks for Augmenting Large Language Models with Temporal Knowledge Graphs in Continuous Learning

arXiv 2606.15778 ↗First posted 14 Jun 2026cs.CL cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) struggle to incorporate new knowledge without forgetting or costly retraining. We propose DYNA, a lightweight framework that augments a frozen LLM with a temporal knowledge graph where events are nodes and temporal relations are directed, timestamped edges. The graph serves as an external, updatable memory. At query time, DYNA retrieves relevant nodes via random walks and centrality measures, then augments the LLM's response. Evaluated on three temporal recall tasks, DYNA reduces catastrophic forgetting by ~7% compared to fine-tuning and improves temporal ordering by ~5% over standard RAG. Higher graph clustering coefficients correlate with better retrieval, showing that graph structure matters. Contributions: (1) episodic memory as temporal KG, (2) retraining-free LLM augmentation, (3) graph properties as predictors of retrieval performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 14 Jun 2026.

Builds on

18 of 35 references.

References · 18

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 622
  6. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  7. 2022Deep Bidirectional Language-Knowledge Graph Pretrainingcited by 156
  8. 2017Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphscited by 149
  9. 2024Continual Learning for Large Language Models: A Surveycited by 144
  10. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  11. 2022Temporal Knowledge Graph Reasoning with Historical Contrastive Learningcited by 42
  12. 2024Memory3: Language Modeling with Explicit Memorycited by 39
6 more
  1. 2024A Survey on Temporal Knowledge Graph: Representation Learning and Applicationscited by 30
  2. 2022Inductive Logical Query Answering in Knowledge Graphscited by 25
  3. 2023Semantic HELM: A Human-Readable Memory for Reinforcement Learningcited by 17
  4. 2023ConPET: Continual Parameter-Efficient Tuning for Large Language Modelscited by 16
  5. 2020Neurocoder: Learning General-Purpose Computation Using Stored Neural Programscited by 6
  6. 2025Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Studycited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning
  2. 2025DySK-Attn: A Framework for Efficient, Real-Time Knowledge Updating in Large Language Models via Dynamic Sparse Knowledge Attention
  3. 2024Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion
  4. 2026REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMs
  5. 2025PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents
  6. 2025T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval
  7. 2026MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
  8. 2026LLM-Guided Knowledge Distillation for Temporal Knowledge Graph Reasoning