Active Inference: A Method For Phenotyping Agency In AI Systems?

Abstract

arXiv:2604.23278v1 Announce Type: new 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-, in

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywilson2026active

Related papers

• Active Inference As A Model Of Agency (2024)0.00
• Expanding The Active Inference Landscape: More Intrinsic Motivations In The Perception-action Loop (2018)9.92
• Deep Active Inference Agents Using Monte-carlo Methods (2020)0.00
• Active Inference: Demystified And Compared (2019)15.98
• A Mathematical Theory Of Agency And Intelligence (2026)0.00
• Sophisticated Inference (2020)14.83
• Contrastive Active Inference (2021)0.00
• Deconstructing Deep Active Inference (2023)2.26