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

• URL: http://arxiv.org/abs/2605.05097v2
• Date: Thu, 07 May 2026 10:27:04 GMT
• Title: Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
• Abstract summary: We argue that external memory should follow a similar principle to biological memory.<n>In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph.
• Score: 5.113513399537608
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics.

Related papers

• Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation [27.410703803632718]
  We propose a framework that shifts memory management to the write phase through cost-aware routing and periodic parametric consolidation.<n>A 1.7B/8B cascade prunes up to 68% of redundant external memory while escalating fewer than 50% of inputs.<n>We further show that periodic consolidation successfully internalizes external knowledge, allowing the router to adaptively suppress redundant writes as the model's boundaries evolve.
  arXiv  Detail & Related papers  (2026-08-23T04:40:13Z)
• HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents [8.86975756125001]
  HeLa-Mem is a bio-inspired memory architecture that models memory as a dynamic graph with Hebbian learning dynamics.<n>HeLa-Mem employs a dual-level organization: (1) an episodic memory graph that evolves through co-activation patterns, and (2) a semantic memory store populated via Hebbian Distillation.<n> Experiments on LoCoMo demonstrate superior performance across four question categories while using significantly fewer context tokens.
  arXiv  Detail & Related papers  (2026-04-18T05:11:18Z)
• Social Hippocampus Memory Learning [54.381608978482184]
  SoHip is a memory-centric social machine learning framework.<n>It enables collaboration among heterogeneous agents via memory sharing rather than model sharing.<n>Experiments on two benchmark datasets with seven baselines demonstrate that SoHip consistently outperforms existing methods.
  arXiv  Detail & Related papers  (2026-03-26T16:31:00Z)
• The AI Hippocampus: How Far are We From Human Memory? [77.04745635827278]
  Implicit memory refers to the knowledge embedded within the internal parameters of pre-trained transformers.<n>Explicit memory involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations.<n>Agentic memory introduces persistent, temporally extended memory structures within autonomous agents.
  arXiv  Detail & Related papers  (2026-01-14T03:24:08Z)
• MemVerse: Multimodal Memory for Lifelong Learning Agents [35.218549149012844]
  We introduce MemVerse, a model-agnostic, plug-and-play memory framework.<n>MemVerse bridges fast parametric recall with hierarchical retrieval-based memory.<n>It enables scalable and adaptive multimodal intelligence.
  arXiv  Detail & Related papers  (2025-12-03T10:06:14Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• MemGen: Weaving Generative Latent Memory for Self-Evolving Agents [57.1835920227202]
  We propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty.<n>MemGen enables agents to recall and augment latent memory throughout reasoning, producing a tightly interwoven cycle of memory and cognition.
  arXiv  Detail & Related papers  (2025-09-29T12:33:13Z)
• MemOS: A Memory OS for AI System [116.87568350346537]
  Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI)<n>Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.<n>MemOS is a memory operating system that treats memory as a manageable system resource.
  arXiv  Detail & Related papers  (2025-07-04T17:21:46Z)
• Memorization and Knowledge Injection in Gated LLMs [8.305942415868042]
  Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge.<n>Memory Embedded in Gated LLMs (MEGa) injects event memories directly into the weights of LLMs.<n>During inference, a gating mechanism activates relevant memory weights by matching query embeddings to stored memory embeddings.
  arXiv  Detail & Related papers  (2025-04-30T00:28:32Z)
• Energy-based General Sequential Episodic Memory Networks at the Adiabatic Limit [3.5450828190071655]
  We introduce a new class of General Sequential Episodic Memory Models (GSEMM) The dynamic energy surface is enabled by newly introduced asymmetric synapses with signal propagation delays in the network's hidden layer. We show that DSEM has a storage capacity that grows exponentially with the number of neurons in the network.
  arXiv  Detail & Related papers  (2022-12-11T18:09:34Z)
• Self-Attentive Associative Memory [69.40038844695917]
  We propose to separate the storage of individual experiences (item memory) and their occurring relationships (relational memory) We achieve competitive results with our proposed two-memory model in a diversity of machine learning tasks.
  arXiv  Detail & Related papers  (2020-02-10T03:27:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.