A single mathematical formula now bridges the gap between how brains learn, how markets settle, and how heat moves.
Science has long treated Bayesian inference, Game Theory, and Thermodynamics as separate fields. This new Game-Theoretic Free Energy Principle provides a unified framework for all of them. It shows that multi-agent systems naturally move toward Nash equilibria as they minimize their local free energy. This bridge allows researchers to use tools from physics to predict the behavior of economic markets or AI swarms. It creates a universal language for understanding any system that processes information and energy. The same laws that cool a cup of coffee might also govern the future of global finance.
A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics
arXiv · 2604.27942
Collective intelligence emerges across biological, physical, and artificial systems without central coordination, yet a unifying principle governing such behaviour remains elusive. The Free Energy Principle explains how individual agents adapt through variational inference, while game theory formalises strategic interactions. Here we introduce the Game-Theoretic Free Energy Principle, a unified framework showing that multi-agent systems performing local free-energy minimisation implicitly implem