aiqbench analysis
This paper uses collective predictive coding, a framework from language-emergence research, to learn macroscopic order parameters from raw spin configurations without knowing the microscopic Hamiltonian. It is tested only on classical spin models (Ising, stripe-ordered, and Sherrington-Kirkpatrick spin glass), so the claims are limited to those settings. For ML readers, the interest is in a data-driven representation learning method applied to physics, with the open question being how far it generalizes beyond toy models.
Atom as an Agent: Emergent Order by Collective Predictive Coding
arXiv:2610.36673v1 Announce Type: cross Abstract: What is the intrinsic reason of emergence of macroscopic order parameter out of microscopic systems? In this article, we apply to physics the collective predictive coding (CPC), the theory of language/symbol emergence. As our language emerges out of our human communications, physical macroscopic order parameter emerges out of communications among atoms --- each atom is regarded as an agent who predicts each other's behavior through inference. We present three examples of classical spin systems: two-dimensional ferromagnetic and antiferromagnetic Ising models, a two-dimensional spin model with competing stripe orders, and the fully connected Sherrington--Kirkpatrick spin-glass model. In all of these examples, proper macroscopic order parameters including the replica overlap emerge automatically through communication informatics of CPC, only from observed spin configurations. We call the learned macroscopic coordinate the collective predictive order. Furthermore, for the ferromagnetic and antiferromagnetic Ising models, the equilibrium distribution of the collective predictive order yields an emergent potential with the symmetry and thermal evolution characteristic of a Landau potential. Notably, the emergence of the collective predictive order does not refer to any structure of microscopic Hamiltonians/Lagrangians. Thus our ``Atom-as-an-Agent" (AaaA) principle offers a completely data-driven method for the emergence of macroscopic order, that is, machine learning physics.
Abstract:What is the intrinsic reason of emergence of macroscopic order parameter out of microscopic systems? In this article, we apply to physics the collective predictive coding (CPC), the theory of language/symbol emergence. As our language emerges out of our human communications, physical macroscopic order parameter emerges out of communications among atoms --- each atom is regarded as an agent who predicts each other's behavior through inference. We present three examples of classical spin systems: two-dimensional ferromagnetic and antiferromagnetic Ising models, a two-dimensional spin model with competing stripe orders, and the fully connected Sherrington--Kirkpatrick spin-glass model. In all of these examples, proper macroscopic order parameters including the replica overlap emerge automatically through communication informatics of CPC, only from observed spin configurations. We call the learned macroscopic coordinate the collective predictive order. Furthermore, for the ferromagnetic and antiferromagnetic Ising models, the equilibrium distribution of the collective predictive order yields an emergent potential with the symmetry and thermal evolution characteristic of a Landau potential. Notably, the emergence of the collective predictive order does not refer to any structure of microscopic Hamiltonians/Lagrangians. Thus our ``Atom-as-an-Agent" (AaaA) principle offers a completely data-driven method for the emergence of macroscopic order, that is, machine learning physics.
Disordered Systems and Neural Networks (cond-mat.dis-nn); Statistical Mechanics (cond-mat.stat-mech); Artificial Intelligence (cs.AI); High Energy Physics - Theory (hep-th)
arXiv:2610.36673 [cond-mat.dis-nn]
(or arXiv:2610.36673v1 [cond-mat.dis-nn] for this version)
https://doi.org/10.48550/arXiv.2610.36673 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 232 words
Related coverage
Collective Epistemics: Napkin Math on Independent Errors
LessWrong · Sep 18, 2026
One Future, Every Robot: Label-Efficient Collective-State Prediction with Decentralized JEPA
arXiv · Jul 31, 2026
Local Predictability and Collective Fidelity in LLM-Agent Societies
arXiv · Oct 1, 2026
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
arXiv · Aug 21, 2026