Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Qi, Li, Kun, Han, Haozhi, Shang, Honghui, He, Xinfu, Zhang, Yunquan, An, Hong, Cao, Ting, Yang, Mao
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.20094
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913919763742720
author Li, Qi
Li, Kun
Han, Haozhi
Shang, Honghui
He, Xinfu
Zhang, Yunquan
An, Hong
Cao, Ting
Yang, Mao
author_facet Li, Qi
Li, Kun
Han, Haozhi
Shang, Honghui
He, Xinfu
Zhang, Yunquan
An, Hong
Cao, Ting
Yang, Mao
contents Can a scientific simulation system be physically consistent, interpretable by design, and scalable across regimes--all at once? Despite decades of progress, this trifecta remains elusive. Classical methods like Kinetic Monte Carlo ensure thermodynamic accuracy but scale poorly; learning-based methods offer efficiency but often sacrifice physical consistency and interpretability. We present SwarmThinkers, a reinforcement learning framework that recasts atomic-scale simulation as a physically grounded swarm intelligence system. Each diffusing particle is modeled as a local decision-making agent that selects transitions via a shared policy network trained under thermodynamic constraints. A reweighting mechanism fuses learned preferences with transition rates, preserving statistical fidelity while enabling interpretable, step-wise decision making. Training follows a centralized-training, decentralized-execution paradigm, allowing the policy to generalize across system sizes, concentrations, and temperatures without retraining. On a benchmark simulating radiation-induced Fe-Cu alloy precipitation, SwarmThinkers is the first system to achieve full-scale, physically consistent simulation on a single A100 GPU, previously attainable only via OpenKMC on a supercomputer. It delivers up to 4963x (3185x on average) faster computation with 485x lower memory usage. By treating particles as decision-makers, not passive samplers, SwarmThinkers marks a paradigm shift in scientific simulation--one that unifies physical consistency, interpretability, and scalability through agent-driven intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale
Li, Qi
Li, Kun
Han, Haozhi
Shang, Honghui
He, Xinfu
Zhang, Yunquan
An, Hong
Cao, Ting
Yang, Mao
Artificial Intelligence
Can a scientific simulation system be physically consistent, interpretable by design, and scalable across regimes--all at once? Despite decades of progress, this trifecta remains elusive. Classical methods like Kinetic Monte Carlo ensure thermodynamic accuracy but scale poorly; learning-based methods offer efficiency but often sacrifice physical consistency and interpretability. We present SwarmThinkers, a reinforcement learning framework that recasts atomic-scale simulation as a physically grounded swarm intelligence system. Each diffusing particle is modeled as a local decision-making agent that selects transitions via a shared policy network trained under thermodynamic constraints. A reweighting mechanism fuses learned preferences with transition rates, preserving statistical fidelity while enabling interpretable, step-wise decision making. Training follows a centralized-training, decentralized-execution paradigm, allowing the policy to generalize across system sizes, concentrations, and temperatures without retraining. On a benchmark simulating radiation-induced Fe-Cu alloy precipitation, SwarmThinkers is the first system to achieve full-scale, physically consistent simulation on a single A100 GPU, previously attainable only via OpenKMC on a supercomputer. It delivers up to 4963x (3185x on average) faster computation with 485x lower memory usage. By treating particles as decision-makers, not passive samplers, SwarmThinkers marks a paradigm shift in scientific simulation--one that unifies physical consistency, interpretability, and scalability through agent-driven intelligence.
title SwarmThinkers: Learning Physically Consistent Atomic KMC Transitions at Scale
topic Artificial Intelligence
url https://arxiv.org/abs/2505.20094