Automated scientific minimization of regret

2025-05-23

AI Summary

This study addresses the limitation in interpretable cognitive modeling where manually constructed models often omit critical mechanisms, thereby constraining predictive performance. We propose the first fully automated cognitive modeling framework: it leverages the Centaur foundational human cognitive model to diagnose structural deficiencies in existing interpretable models; employs a language reasoning model to generate semantically coherent, mechanism-explicit corrections; and optimizes revisions via scientific regret minimization. Applied to multi-attribute decision-making paradigms, our method achieves end-to-end automated modeling while rigorously preserving interpretability—achieving, for the first time, behavioral prediction accuracy at the human behavioral noise ceiling. The core contribution lies in shifting cognitive modeling from expert-dependent construction to a closed-loop, data- and knowledge-coordinated automation paradigm.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We introduce automated scientific minimization of regret (ASMR) -- a framework for automated computational cognitive science. Building on the principles of scientific regret minimization, ASMR leverages Centaur -- a recently proposed foundation model of human cognition -- to identify gaps in an interpretable cognitive model. These gaps are then addressed through automated revisions generated by a language-based reasoning model. We demonstrate the utility of this approach in a multi-attribute decision-making task, showing that ASMR discovers cognitive models that predict human behavior at noise ceiling while retaining interpretability. Taken together, our results highlight the potential of ASMR to automate core components of the cognitive modeling pipeline.

Problem

• Automated framework for computational cognitive science
• Identifies gaps in interpretable cognitive models
• Improves human behavior prediction while maintaining interpretability

Innovation

• Automated scientific regret minimization framework
• Leverages Centaur model for cognitive gaps
• Language-based reasoning for model revisions