Agentic AI Reference Architecture

Model Adaptation · Software component

Revealed Preference Learner

Software componentModel AdaptationModelsarc:RevealedPreferenceLearner

A preference elicitor that updates utility weights from which presented options users select and from outcome feedback, learning weights that best explain observed choices.

Responsibility. Learns personalized utility weights from users' revealed choices and feedback.

Also known as: Adaptive utility learning, Implicit weight learning, Suggestion-rejection learner

Variant of Preference Elicitor abstract

When to choose. Choose when users' selections among presented options and feedback are continuously observable, enabling personalization without explicit preference configuration.

readsreceives data fromis target of alternativeTowritesspecializeswritesUser Feedback Store: readsUser Feedback StoreBehavioral Signal Tracker: receives data fromBehavioral Signal TrackerInverse Reward Learner: is target of alternativeToInverse Reward LearnerUser Preference Profile Store: writesUser Preference Profile …Preference Elicitor: specializesPreference ElicitorValue Priority Profile Store: writesValue Priority Profile S…
Direct neighbourhood (hover for relationship types)

Relationships

reads dependency

writes dependency

receives data from dynamic

alternative to variability

Classification

Patterns
Revealed-preference weight inferenceContextual preference learningRevealed-value observation
Quality attributes
Interaction capability (ISO/IEC 25010)Flexibility (ISO/IEC 25010)

Sources

  1. Ch5.10: T. Nguyen, "Utility-Based Decision Making Fundamentals," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.10. ISBN: 9798244538229.
  2. Ch9.6: T. Nguyen, "Value Alignment Frameworks," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.6. ISBN: 9798244538229.
  3. Ch10.2: T. Nguyen, "Proactive Agents," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.2. ISBN: 9798244538229.