In a reward-free active inference agent, Φr localizes to the slow perspective latent g, its aggregate magnitude comes from the recurrent architecture rather than learning, and learning only becomes visible as a decoupling sign flip plus regime-invariant stability.
Proceedings of the AAAI Symposium Series8(1), 309–315 (May 2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Perspective Latents as an Architectural Condition for Causal Emergence in Active Inference Agents
In a reward-free active inference agent, Φr localizes to the slow perspective latent g, its aggregate magnitude comes from the recurrent architecture rather than learning, and learning only becomes visible as a decoupling sign flip plus regime-invariant stability.