Representation Stability in a Minimal Continual Learning Agent

Continual learning systems are increasingly deployed in environments where retraining or reset isinfeasible, yet many approaches emphasize task performance rather than the evolution of internal representations over time. In this work, we study a minimal continual learning agent designed to isolate representational dynamics from architectural complexity and optimization objectives. The agent maintainsa persistent state vector across executions and incrementally updates it as new textual data is introduced.We quantify representational change using cosine similarity between successive normalized statevectors and define a stability metric over time intervals. Longitudinal experiments across eight executions reveal a transition from an initial plastic regime to a stable representational regime under consistentinput. A deliberately introduced semantic perturbation produces a bounded decrease in similarity (from0.9868 to 0.8957), followed by recovery and re-stabilization under subsequent coherent input.These results demonstrate that meaningful stability–plasticity trade-offs can emerge in a minimal,stateful learning system without explicit regularization, replay, or architectural complexity. The workestablishes a transparent empirical baseline for studying representational accumulation and adaptation incontinual learning systems.