Automated scientific minimization of regret

TL;DR

The paper presents ASMR, an automated framework that uses foundation models and language reasoning to improve cognitive models by identifying and fixing gaps, achieving high predictive accuracy and interpretability.

Contribution

Introduces ASMR, a novel automated approach combining foundation models and language reasoning to enhance cognitive modeling processes.

Findings

ASMR predicts human behavior at noise ceiling.

Models remain interpretable after automated revisions.

Demonstrated effectiveness in multi-attribute decision-making tasks.

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.