# Agentic Information Theory: Ergodicity and Intrinsic Semantics of Information Processes

arXiv: https://arxiv.org/abs/2505.19275 · HTML: https://mlsanity.com/paper/2505.19275/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 75 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 8 of 8)

- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Thermodynamic Computing System for AI Applications](https://mlsanity.com/paper/2312.04836/) (2023)
- [Thermodynamic AI and the fluctuation frontier](https://mlsanity.com/paper/2302.06584/) (2023)
- [Bayesian Structural Inference for Hidden Processes](https://mlsanity.com/paper/1309.1392/) (2013)
- [Topology, Convergence, and Reconstruction of Predictive States](https://mlsanity.com/paper/2109.09203/) (2021)
- [A Theoretical Connection Between Statistical Physics and Reinforcement Learning](https://mlsanity.com/paper/1906.10228/) (2019)
- [The Elusive Present: Hidden Past and Future Dependency and Why We Build Models](https://mlsanity.com/paper/1507.00672/) (2015)

## Abstract (arXiv)

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.