Cognition · Software component

Replan Trigger Threshold Learner

Software componentCognitionCognition & Memoryarc:ReplanTriggerThresholdLearner

A learning component that trains a classifier on historical flagged and ignored discrepancies and their outcomes to adjust replanning thresholds per context.

Responsibility. Adapts replanning trigger thresholds from historical discrepancy outcomes.

Also known as: Adaptive thresholding classifier

Direct neighbourhood (hover for relationship types)

Relationships

reads dependency

Execution Failure History Store Ch5.6

writes dependency

Replan Trigger Threshold Policy Ch5.6

Design guidance

SHOULD make thresholds more aggressive where discrepancies frequently predict failures and more conservative where they rarely matter.

Classification

Patterns: Adaptive thresholding

Sources

Ch5.6: T. Nguyen, "A* Search and Replaning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.6. ISBN: 9798244538229.