Active Inference: A method for Phenotyping Agency in AI systems?

2026-04-25

AI Summary

This study addresses the absence of a testable theoretical framework for agency in current artificial intelligence systems. Building upon three core criteria—intentionality, rationality, and explainability—the authors propose an active inference model centered on variational free energy minimization and conduct computational phenotyping within a T-maze paradigm. Innovatively adopting “empowerment” as an operational metric for graded agency, they integrate partially observable Markov decision processes with structural interventions in generative models to successfully identify three distinct agency phenotypes: low, medium, and high. The findings demonstrate that effective AI governance should shift from external constraints toward modulating the system’s internal prior preferences, thereby offering both theoretical grounding and methodological tools for developing interpretable and controllable artificial intelligence.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

The proliferation of agentic artificial intelligence has outpaced the conceptual tools needed to characterize agency in computational systems. Prevailing definitions mainly rely on autonomy and goal-directedness. Here, we argue for a minimal notion open to principled inspection given three criteria: intentionality as action grounded in beliefs and desires, rationality as normatively coherent action entailed by a world model, and explainability as action causally traceable to internal states; we subsequently instantiate these as a partially observable Markov decision process under a variational framework wherein posterior beliefs, prior preferences, and the minimization of expected free energy jointly constitute an agentic action chain. Using a canonical T-maze paradigm, we evidence how empowerment, formulated as the channel capacity between actions and anticipated observations, serves as an operational metric that distinguishes zero-, intermediate-, and high-agency phenotypes through structural manipulations of the generative model. We conclude by arguing that as agents engage in epistemic foraging to resolve ambiguity, the governance controls that remain effective must shift systematically from external constraints to the internal modulation of prior preferences, offering a principled, variational bridge from computational phenotyping to AI governance strategy

Problem

• agency
• artificial intelligence
• phenotyping
• intentionality
• explainability

Innovation

• Active Inference
• Agency Phenotyping
• Empowerment
• Variational Free Energy
• Epistemic Foraging