A Mathematical Theory Of Agency And Intelligence

Abstract

To operate reliably under changing conditions, complex systems require feedback on how effectively they use resources, not just whether objectives are met. Current AI systems process vast information to produce sophisticated predictions, yet predictions can appear successful while the underlying interaction with the environment degrades. What is missing is a principled measure of how much of the total information a system deploys is actually shared between its observations, actions, and outcomes. We prove this shared fraction, which we term bipredictability, P, is intrinsic to any interaction, derivable from first principles, and strictly bounded: P can reach unity in quantum systems, P equal to, or smaller than 0.5 in classical systems, and lower once agency (action selection) is introduced. We confirm these bounds in a physical system (double pendulum), reinforcement learning agents, and multi turn LLM conversations. These results distinguish agency from intelligence: agency is the c

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhafez2026a

Related papers

• Active Inference: A Method For Phenotyping Agency In AI Systems? (2026)0.00
• Active Inference As A Model Of Agency (2024)0.00
• On The Statistical Limits Of Self-improving Agents (2025)0.00
• Embedded Universal Predictive Intelligence: A Coherent Framework For Multi-agent Learning (2025)0.00
• Information-theoretic Methods For Planning And Learning In Partially Observable Markov Decision Processes (2016)0.00
• Humancompatible.interconnect: Testing Properties Of Repeated Uses Of Interconnections Of AI Systems (2025)0.00
• The Agent Capability Problem: Predicting Solvability Through Information-theoretic Bounds (2025)0.00
• MACIE: Multi-agent Causal Intelligence Explainer For Collective Behavior Understanding (2025)2.26