Active Inference: A method for Phenotyping Agency in AI systems?
Authors: Philip Wilson, Axel Constant, Mahault Albarracin, Nicolás Hinrichs, Jasmine Moore, Daniel Polani, Karl Friston
Organizations: Independent Researcher · Department of Engineering and Informatics, University of Sussex, Falmer, Brighton, BN1 9RH, UK · Laboratoire d’Analyse Cognitive de l’Information, Université du Québec à Montréal, Québec, Canada · Centre of Excellence for AI and Robotics, Sheffield Hallam University, Sheffield, UK · Methods and Development Group Neural Data Science and Statistical Computing, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany · Department of Computer Science, School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield, UK · Wellcome Centre for Human Neuroimaging, University College London, London, UK
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