Parent-Guided Adaptive Reliability (PGAR): A Behavioural Meta-Learning Framework for Stable and Trustworthy AI

TL;DR

PGAR is a lightweight meta-learning framework that enhances AI stability and trustworthiness by adaptively modulating learning rates based on a reliability index derived from reflex signals, improving calibration and recovery.

Contribution

Introduces PGAR, a novel behavioural meta-learning framework with a supervisory layer that adaptively manages learning stability and trustworthiness in AI systems.

Findings

Improves calibration and reduces loss variance.

Enables faster recovery from disturbances.

Retains computational simplicity.

Abstract

Parent-Guided Adaptive Reliability (PGAR) is a lightweight behavioural meta-learning framework that adds a supervisory "parent" layer on top of a standard learner to improve stability, calibration, and recovery under disturbances. PGAR computes three reflex-level signals (incident detection, overconfidence correction, and recovery memory) and fuses them into a bounded reliability index in [0,1]. This index continuously modulates the learner's effective learning rate, reducing update magnitude during instability and restoring it as reliability improves. We provide a Lyapunov-based proof sketch establishing bounded adaptation of the reliability dynamics under mild assumptions (smooth loss, descent direction, and bounded reflex outputs). Empirical evaluations on representative learning tasks show improved calibration, reduced loss variance, and faster recovery compared to standard optimizers, while retaining computational simplicity. PGAR functions as a plug-in reliability layer for existing optimization and learning pipelines, supporting interpretable reliability traces in safety-relevant settings.