Fine-Tuning Small Reasoning Models for Quantum Field Theory
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913050737508352 |
|---|---|
| author | Woodward, Nathaniel S. Gao, Zhiqi Kvasiuk, Yurii Smith, Kendrick M. Sala, Frederic Münchmeyer, Moritz |
| author_facet | Woodward, Nathaniel S. Gao, Zhiqi Kvasiuk, Yurii Smith, Kendrick M. Sala, Frederic Münchmeyer, Moritz |
| contents | Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific physics reasoning ability develops while training these models. To investigate this, we perform the first academic fine-tuning study of small (7B-parameter) reasoning models dedicated specifically to theoretical physics. Because open-source verifiable training data required to train such capabilities is scarce, we developed a robust data generation pipeline that can both create synthetic problems and make existing human-authored problems suitable for model training. Selecting Quantum Field Theory (QFT) as our primary domain, we generated over 2,500 synthetic problems alongside a curated collection of human-adapted problems sourced from arXiv and standard pedagogical resources. We conduct both Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) experiments, benchmarking performance gains as well as generalization to other physics domains. We perform an extensive analysis of model chains-of-though before and after fine-tuning, to understand how reasoning errors evolve during RL and SFT. Finally, we publicly release our data pipeline, verifiable QFT training data, and $\sim$200M tokens of QFT reasoning traces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18936 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Small Reasoning Models for Quantum Field Theory Woodward, Nathaniel S. Gao, Zhiqi Kvasiuk, Yurii Smith, Kendrick M. Sala, Frederic Münchmeyer, Moritz Machine Learning Artificial Intelligence High Energy Physics - Phenomenology High Energy Physics - Theory Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific physics reasoning ability develops while training these models. To investigate this, we perform the first academic fine-tuning study of small (7B-parameter) reasoning models dedicated specifically to theoretical physics. Because open-source verifiable training data required to train such capabilities is scarce, we developed a robust data generation pipeline that can both create synthetic problems and make existing human-authored problems suitable for model training. Selecting Quantum Field Theory (QFT) as our primary domain, we generated over 2,500 synthetic problems alongside a curated collection of human-adapted problems sourced from arXiv and standard pedagogical resources. We conduct both Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) experiments, benchmarking performance gains as well as generalization to other physics domains. We perform an extensive analysis of model chains-of-though before and after fine-tuning, to understand how reasoning errors evolve during RL and SFT. Finally, we publicly release our data pipeline, verifiable QFT training data, and $\sim$200M tokens of QFT reasoning traces. |
| title | Fine-Tuning Small Reasoning Models for Quantum Field Theory |
| topic | Machine Learning Artificial Intelligence High Energy Physics - Phenomenology High Energy Physics - Theory |
| url | https://arxiv.org/abs/2604.18936 |