Agentic Information Theory: Ergodicity and Intrinsic Semantics of Information Processes

James P. Crutchfield, Alexandra Jurgens
5/25/2025
cond-mat.stat-mechcs.ITcs.MA

No confident code implementation found for this paper.

Abstract

We develop information theory for the temporal behavior of memoryful agents moving through complex -- structured, stochastic -- environments. We introduce and explore information processes -- stochastic processes produced by cognitive agents in real-time as they interact with and interpret incoming stimuli. We provide basic results on the ergodicity and semantics of the resulting time series of Shannon information measures that monitor an agent's adapting view of uncertainty and structural correlation in its environment.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Information Flow Rate for Cross-Correlated Stochastic Processes

81% match2024

The Value of Information in Multi-Scale Feedback Systems

80% match2025

Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamics

79% match2026

Emergent Coordination in Multi-Agent Language Models

79% match2025

Characterizing Agent-Based Model Dynamics via ε-Machines and Kolmogorov-Style Complexity

78% match2025

Effective Exploration Based on the Structural Information Principles

78% match2024

Cite this paper

@article{crutchfield2025agentic,
  title  = {Agentic Information Theory: Ergodicity and Intrinsic Semantics of Information Processes},
  author = {James P. Crutchfield and Alexandra Jurgens},
  year   = {2025},
  eprint = {2505.19275},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.19275v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.19275.svg)](https://codeofpaper.com/paper/2505.19275)

Discussion