Agentic Information Theory: Ergodicity and Intrinsic Semantics of Information Processes
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
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.
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.
Builds on
8 of 75 references.
References · 8
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2021Embodied Intelligence via Learning and Evolutioncited by 163
- 2023Thermodynamic Computing System for AI Applicationscited by 16
- 2023Thermodynamic AI and the fluctuation frontiercited by 15
- 2013Bayesian Structural Inference for Hidden Processescited by 5
- 2021Topology, Convergence, and Reconstruction of Predictive Statescited by 5
- 2019A Theoretical Connection Between Statistical Physics and Reinforcement Learningcited by 4
- 2015The Elusive Present: Hidden Past and Future Dependency and Why We Build Modelscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Emergence of Physical Intelligence via Controllable Information Production
- 2025An Information Theoretic Perspective on Agentic System Design
- 2025Mutual Information Tracks Policy Coherence in Reinforcement Learning
- 2026SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory
- 2026Cognitive Cells: A Compositional Framework for Populations of Small Language Models
- 2025Memory in the Age of AI Agents
- 2026What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
- 2026World Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents