{"slug": "perspective-latents-as-an-architectural-condition-for-causal-emergence-in-active", "title": "Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents", "summary": "A new study tests causal emergence in an active inference agent whose architecture separates a fast perception latent z from a slow global latent g, finding that the integrated information measure Φr concentrates in g and is largely architectural, decreasing with training. The substantive learning effect appears only at the atom-compositional level, where decoupling flips sign from negative to positive and becomes regime-invariant, while downward causation carries regime-dependent adjustment. The results identify g as the architectural locus of Φr-relevant temporal organization and argue against reading scalar Φr as a direct index of learned integration.", "body_md": "arXiv:2607.20708v1 Announce Type: new\nAbstract: A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $\\Phi_r$ 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, $\\Phi_r$ 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 $\\Phi_r$-relevant temporal organization in an active inference agent, and argue against reading scalar $\\Phi_r$ as a direct index of learned integration.", "url": "https://wpnews.pro/news/perspective-latents-as-an-architectural-condition-for-causal-emergence-in-active", "canonical_source": "https://www.machinebrief.com/news/perspective-latents-as-an-architectural-condition-for-causal-30ew", "published_at": "2026-07-24 04:00:00+00:00", "updated_at": "2026-07-24 04:38:26.348862+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "neural-networks"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/perspective-latents-as-an-architectural-condition-for-causal-emergence-in-active", "markdown": "https://wpnews.pro/news/perspective-latents-as-an-architectural-condition-for-causal-emergence-in-active.md", "text": "https://wpnews.pro/news/perspective-latents-as-an-architectural-condition-for-causal-emergence-in-active.txt", "jsonld": "https://wpnews.pro/news/perspective-latents-as-an-architectural-condition-for-causal-emergence-in-active.jsonld"}}