arXiv Machine Learning July 24, 2026 By Hongju Pae

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

Read the original on arXiv Machine Learning →

arXiv:2607. 20708v1 Announce Type: new Abstract: 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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 15

When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary

arXiv:2607. 11953v1 Announce Type: new Abstract: Does a reinforcement-learning agent that earns high reward represent its task's latent state, or only a reward-correlated shortcut?

By Jim Allchin

agents reinforcement-learning

arXiv AI

Aug 5

Quo Vadis, World Modeling?

arXiv:2608. 02713v1 Announce Type: cross Abstract: Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize.

By Yu Yang, Xuemeng Yang, Licheng Wen, Lingdong Kong, Xiaobin Hu, Dongyue Lu, Wei Chow, Xiyan Huang, Yuxiang Feng, Yue Liao, Jianbiao Mei, Daocheng Fu, Rong Wu, Pinlong Cai, Ran Yi, Ying Tai, Jiangning Zhang, Botian Shi, Yong Liu, Shuicheng Yan

agents

arXiv Machine Learning

Jul 15

Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle

arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.

By MD Ibrahim Hossain Ridoy

diffusion

Hugging Face Trending Papers

Aug 3

Quo Vadis, World Modeling?

Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions.

agents

arXiv AI

Jun 2

TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications

arXiv:2606. 01520v1 Announce Type: new Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or a financial order book.

By Shayan Shokri

rag nlp reinforcement-learning robotics

arXiv Machine Learning

Aug 4

Emergence Invariance: From Symbolized Thought to Interface Refinement

arXiv:2608. 01548v1 Announce Type: cross Abstract: Language can be viewed as a formalized subset of thought: a consequence-governed symbolic structure projected from wider situated cognition.

By Yi Liu

llms agents

Related stories

When Does Reward Teach State? A Hidden-Automaton Instrument and the Group-Language Boundary

Quo Vadis, World Modeling?

Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle

Quo Vadis, World Modeling?

TERRA: Task-Embedded Reasoning and Representation Architecture for Cross-Domain Applications

Emergence Invariance: From Symbolized Thought to Interface Refinement