LLMs with in-context learning for Algorithmic Theoretical Physics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911664079634432 |
|---|---|
| author | Hell, Anamaria Thiele, Leander |
| author_facet | Hell, Anamaria Thiele, Leander |
| contents | There is an increasing number of algorithmic computations in theoretical physics. These, while conceptually simple, can nevertheless be time-consuming and contain subtleties that should not be overlooked. Given the recent improvement of Large Language Models (LLM), it is natural to investigate whether LLMs equipped with a computer algebra system (CAS) runtime and sufficiently informative context can reliably carry out these algorithmic tasks. In this work, we interface Claude with Maple, and apply this framework to cosmological perturbations in modified theories of gravity. We demonstrate the current capabilities of this approach, the typical failures, and how the same can be improved. We find that a frontier LLM supplied with worked examples is able to solve most test problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08212 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLMs with in-context learning for Algorithmic Theoretical Physics Hell, Anamaria Thiele, Leander Machine Learning Computation and Language General Relativity and Quantum Cosmology High Energy Physics - Theory There is an increasing number of algorithmic computations in theoretical physics. These, while conceptually simple, can nevertheless be time-consuming and contain subtleties that should not be overlooked. Given the recent improvement of Large Language Models (LLM), it is natural to investigate whether LLMs equipped with a computer algebra system (CAS) runtime and sufficiently informative context can reliably carry out these algorithmic tasks. In this work, we interface Claude with Maple, and apply this framework to cosmological perturbations in modified theories of gravity. We demonstrate the current capabilities of this approach, the typical failures, and how the same can be improved. We find that a frontier LLM supplied with worked examples is able to solve most test problems. |
| title | LLMs with in-context learning for Algorithmic Theoretical Physics |
| topic | Machine Learning Computation and Language General Relativity and Quantum Cosmology High Energy Physics - Theory |
| url | https://arxiv.org/abs/2605.08212 |