Representation Stability in a Minimal Continual Learning Agent

TL;DR

This paper investigates how a simple continual learning agent maintains and adapts its internal representations over time, demonstrating stable and plastic regimes without complex mechanisms.

Contribution

It introduces a minimal, stateful continual learning model and quantifies its representational dynamics, providing a transparent baseline for future research.

Findings

Representational stability emerges over time in the minimal agent.

Semantic perturbations cause bounded decreases in representational similarity.

The system naturally transitions from plasticity to stability without explicit regularization.

Abstract

Continual learning systems are increasingly deployed in environments where retraining or reset is infeasible, 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 maintains a 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 state vectors 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 consistent input. A deliberately introduced semantic perturbation produces a bounded decrease in similarity, followed by recovery and restabilization under subsequent coherent input. These results demonstrate that meaningful stability plasticity tradeoffs can emerge in a minimal, stateful learning system without explicit regularization, replay, or architectural complexity. The work establishes a transparent empirical baseline for studying representational accumulation and adaptation in continual learning systems.