On Agentic Behavioral Modeling

TL;DR

This paper introduces agentic behavioral modeling (ABM), a framework that treats artificial agents as hypotheses about cognitive mechanisms, validated through formal probabilistic models and empirical data in simple tasks.

Contribution

It formalizes ABM, applies it to minimal paradigms, and demonstrates its potential as a foundation for cognitive behavioral science research.

Findings

Validated models using recovery simulations.

Derived optimal policies for tasks.

Showed equivalence between Rescorla-Wagner and Bayesian inference.

Abstract

Integrating theoretical neuroscience, decision theory, and probabilistic inference offers a promising route to understanding human cognition, yet concrete methodological bridges between agentic AI models and behavioral data analysis remain formally underdeveloped. We advance this synthesis under the framework of agentic behavioral modeling (ABM), which treats artificial agents as latent, generative hypotheses about cognitive mechanisms and evaluates them by their statistical adequacy in explaining human behavior. After outlining its conceptual foundations, we apply the framework to two minimal laboratory paradigms: a binary perceptual contrast-discrimination task and a symmetric two-armed bandit learning task. We formalize each task-agent-data system as a joint probability model, derive explicit conditional log-likelihoods for behavioral inference, validate different model variants using model and parameter recovery simulations, and evaluate them in light of empirical data. Using these minimal examples, we provide an agent-centric interpretation of the psychometric function, derive optimal policies for both tasks, and show the equivalence between Rescorla-Wagner learning and Bayesian inference in symmetric bandits. More broadly, this work may serve as a conceptual and practical foundation for applying ABM to cognitive behavioral science.