The paper introduces a framework that separates physical modeling from execution in physics reasoning tasks. It uses a two‑stage post‑training approach: supervised fine‑tuning to build structured models and reinforcement learning with rubric‑based feedback to refine them. Experiments on PhysReason, PhyX, and SeePhys show that this explicit modeling improves reasoning performance by about 3% on average for small LLMs.
By Ye Zhang, Xuehang Guo, Rui Pan, Pengfei Yu, Denghui Zhang, Manling Li, Qingyun Wang
Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order.
arXiv:2603.03517v2 Announce Type: replace-cross
Abstract: General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and perfor...
By Maksim Kuznetsov, Zulfat Miftahutdinov, Rim Shayakhmetov, Mikolaj Mizera, Roman Schutski, Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Thomas MacDougall, Mathieu Reymond, Mihir Bafna, Kaeli Kaymak-Loveless, Eugene Babin, Maxim Malkov, Mathias Lechner, Ramin Hasani, Alexander Amini, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
arXiv:2607. 07708v1 Announce Type: cross Abstract: Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization.
By Chen Tang, Yizhou Wang, Jianyu Wu, Lintao Wang, Shixiang Tang, Pengze Li, Encheng Su, Jun Yao, Jiabei Xiao, Yuqi Shi, Jielan Li, Hongxia Hao, Zhangyang Gao, Fang Wu, Ben Fei, Xiangyu Yue, Pan Tan, Bozitao Zhong, Jinouwen Zhang, Aoran Wang, Yan Lu, Jiaheng Liu, Xinzhu Ma, Liang Hong, Mingyue Zheng, Phil Torr, Bowen Zhou, Wanli Ouyang, Lei Bai
The paper proposes an unsupervised learning approach that uses program synthesis to translate detailed simulation traces into sparse, high‑level structural patterns, making them easier for large language models to interpret. These pattern detectors can be guided by human‑provided labels such as "rigid collision" or "stretching spring" and produce transparent, explainable functions mapping system states to concise annotations. Experiments on a physics benchmark show that the annotated representations improve natural language reasoning about specific physical systems and enable natural‑language goals to be converted into reward programs for solution search.
By Sean Memery, Kartic Subr
arXiv:2503.19081v2 Announce Type: replace
Abstract: Scientific foundation models (SciFMs) aim to learn generalizable representations of physical systems governed by partial differential equations (PD...
By Serge Kotchourko, Amin Totounferoush, Michael W. Mahoney, Steffen Staab