Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents

2026/07/22 by Hongju Pae
#cs.LG #q-bio.NC

paper · pdf

Abstract

A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that Φ_r grows with training and tracks reward improvement. For active inference, this raises the question of how reward-free predictive organization relates to such information-theoretic signatures. I test this within an active inference agent whose architecture separates a fast perception latent z from a slow global latent g, where g is driven by prediction error and structurally decoupled from policy gradients. In a reward-free environmental regime-switching protocol, Φ_r concentrates in g; its aggregate magnitude is largely architectural and decreases with training. The substantive effect of learning becomes legible only at the atom-compositional level: decoupling flips sign from negative to positive and becomes regime-invariant under environmental change, while downward causation carries the regime-dependent adjustment. These results identify g as the architectural locus of Φ_r-relevant temporal organization in an active inference agent, and argue against reading scalar Φ_r as a direct index of learned integration.

Citations

• The Causally Emergent Alignment Hypothesis: Causal Emergence Aligns with and Predicts Final Reward in Reinforcement Learning Agents
• Same World, Differently Given: History-Dependent Perceptual Reorganization in Artificial Agents
• Consciousness as Integrated Information: a Provisional Manifesto

Related

• The Causally Emergent Alignment Hypothesis: Causal Emergence Aligns with and Predicts Final Reward in Reinforcement Learning Agents
• Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
• Scaling active inference
• Active Inference: A Process Theory
• Active Inference as a Model of Agency