APA

(2025). Status and Prospects of AI Reasoning in Theoretical Physics. Perimeter Institute. https://pirsa.org/25080025

MLA

Status and Prospects of AI Reasoning in Theoretical Physics. Perimeter Institute, Aug. 26, 2025, https://pirsa.org/25080025

BibTex

@misc{ pirsa_PIRSA:25080025,
  doi = {10.48660/25080025},
  url = {https://pirsa.org/25080025},
  author = {},
  keywords = {Cosmology, Particle Physics, Strong Gravity},
  language = {en},
  title = {Status and Prospects of AI Reasoning in Theoretical Physics},
  publisher = {Perimeter Institute},
  year = {2025},
  month = {aug},
  note = {PIRSA:25080025 see, \url{https://pirsa.org}}
}
            

Abstract

I will give a brief review of how large-language models are now being used for theoretical physics research. I will show the rapid progress of these models at the example of the TPBench benchmark, and present our recent work on improving their reliability with a symbolic verification agent and test-time scaling techniques. I will also discuss whether these models are truly reasoning and speculate how we might improve their performance in our field in the future.