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

2026-05-06

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.

Problem

• Continual Knowledge Updating
• Multi-Timescale Memory
• External Memory
• Synaptic Consolidation
• Selective Forgetting

Innovation

• continual learning
• multi-timescale memory
• associative memory
• synaptic consolidation
• selective forgetting