# Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics

arXiv: https://arxiv.org/abs/2605.05097 · HTML: https://mlsanity.com/paper/2605.05097/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 19 of 19)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Augmented Language Models: a Survey](https://mlsanity.com/paper/2302.07842/) (2023)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Black-Box Tuning for Language-Model-as-a-Service](https://mlsanity.com/paper/2201.03514/) (2022)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Continual Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2402.01364/) (2024)
- [Nested Learning: The Illusion of Deep Learning Architectures](https://mlsanity.com/paper/2512.24695/) (2025)
- [Continual Reinforcement Learning with Complex Synapses](https://mlsanity.com/paper/1802.07239/) (2018)
- [SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation](https://mlsanity.com/paper/2601.02744/) (2026)
- [Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2602.01965/) (2026)
- [Theories of synaptic memory consolidation and intelligent plasticity for continual learning](https://mlsanity.com/paper/2405.16922/) (2024)
- [Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems](https://mlsanity.com/paper/2512.15922/) (2025)

## Built on by (most cited first, 1 of 1)

- [Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge Updating](https://mlsanity.com/paper/2609.03900/) (2026)

## Abstract (arXiv)

LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting are expected to emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics. This workshop article describes an early-stage conceptual design without experimental evaluation.