Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| 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 |