The Semantic Least-Energy Principle: A Hypothesis for Intelligence

2026-07-27Information Theory

Information Theory
AI summary

The authors suggest a new idea called the Semantic Least-Energy Principle (SLEP) to explain how intelligent systems organize meaning inside their minds. They think intelligent systems try to get the most useful meaning while using the least amount of energy for thinking and predicting. They use math to describe this process and show it can explain things like how concepts are shaped and how reasoning works. Although this idea still needs to be tested, it offers a fresh way to study intelligence in both machines and brains.

Semantic Least-Energy Principlelatent semantic statesvariational frameworksemantic cognitioninformation theorypredictive codinglatent semantic manifoldsemantic utilityoptimization
Authors
Jie Zhang, Haoyuan Zhu, James Jinheng Zhang, Haonan Hu
Abstract
Despite remarkable advances in artificial intelligence and cognitive neuroscience, no generally accepted first-principle explains why intelligent systems organize latent semantic states as they do. Existing frameworks such as information theory, the Information Bottleneck, the Degree of Information Abstraction, predictive coding and the Free Energy Principle provide powerful frameworks for understanding communication, learning, and prediction, but do not explicitly explain the emergence and organization of semantic intelligence. Here we propose the \textbf{Semantic Least-Energy Principle (SLEP)} as a hypothesis that intelligent systems evolve internal representations by maximizing semantic utility while progressively minimizing semantic, predictive, and computational energy. We formulate this hypothesis within a variational framework in which semantic cognition is governed by a Semantic Action Functional whose stationary solutions define efficient trajectories on a latent semantic manifold. This formulation emerges a series of theoretical predictions, including semantic geometry, semantic thermodynamics, and low-energy latent semantic states as complementary consequences of the same underlying optimization process. SLEP unifies semantic abstraction, reasoning, planning, and communication within a common mathematical framework while generating experimentally testable predictions for both artificial and biological intelligence. Although the hypothesis remains to be rigorously validated, it provides a principled foundation for investigating semantic intelligence from a first-principle perspective.