AI-Newton: A concept-driven physical law discovery system without prior physical knowledge
Physical Review Research · 04.11.2026 · 8 (4)
DOI: 10.1103/dvvc-4rsr ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Research, online erschienen am 04.11.2026. Verfasst von You-Le Fang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Peking University.
Abstract (Originalsprache)
While current artificial intelligence (AI)-driven methods excel at deriving empirical models from individual experiments, a significant challenge remains in uncovering the common fundamental physics that underlie these models—a task at which human physicists are adept. To bridge this gap, we introduce AI-Newton, a framework for concept-driven scientific discovery. Our system autonomously derives general physical laws directly from raw, multiexperiment data, operating without supervision or prior physical knowledge. Its core innovations are twofold: (1) proposing interpretable physical concepts to construct laws and (2) progressively generalizing these laws to broader domains. Applied to a large, noisy dataset of mechanics experiments, AI-Newton successfully rediscovers foundational and universal laws, such as Newton's second law, the conservation of energy, and the universal gravitation. This work represents a proof-of-concept step toward autonomous, humanlike scientific discovery.
Förderung
- National Natural Science Foundation of China
- Peking University
Zitieren
APA
Fang, Y., Jian, D., Li, X., & Ma, Y. (2026). AI-Newton: A concept-driven physical law discovery system without prior physical knowledge. Physical Review Research, 8(4). https://doi.org/10.1103/dvvc-4rsr
Vancouver
Fang Y, Jian D, Li X, Ma Y. AI-Newton: A concept-driven physical law discovery system without prior physical knowledge. Physical Review Research. 2026;8(4). doi:10.1103/dvvc-4rsr
BibTeX
@article{Fang2026,
author = {Fang, You-Le and Jian, Dong-Shan and Li, Xiang and Ma, Yan-Qing},
title = {AI-Newton: A concept-driven physical law discovery system without prior physical knowledge},
journal = {Physical Review Research},
year = {2026},
volume = {8},
number = {4},
doi = {10.1103/dvvc-4rsr}
}
EUVIMED