Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks

ArXi:2509.06701v2 Announce Type: replace-cross We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted logarithmic pooling that strictly improves every member's welfare. We prove that strict unanimity is impossible under linear pooling or in binary outcome spaces, but possible with three or outcomes.