| name | perspective-latents-as-an-architectural-condition-for-causal |
| description | Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents |
| metadata | {"arxiv_id":"2607.20708","utility":0.87,"date_added":"2026-07-26"} |
Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
arXiv: 2607.20708
Published: 2026-07-22
Utility: 0.87
Summary
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....
Key Information
- Title: Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
- Authors: [Extract from entry]
- Primary Category: q-bio.NC
Potential Skill Application
This paper presents research relevant to AI agent systems. Consider extracting methodologies, algorithms, or frameworks for skill development.
Reference
