Can Theoretical Physics Research Benefit from Language Agents?

TL;DR

This paper discusses the potential and challenges of applying large language models to theoretical physics, emphasizing the need for domain-specific training and verification tools for meaningful scientific progress.

Contribution

It highlights the gaps in current LLMs for physics and proposes the development of physics-aware AI agents with specialized training and verification frameworks.

Findings

Current LLMs lack physical intuition and reliable reasoning.

Physics-specific training data and verification tools are essential.

Collaborative efforts are needed to develop physics-aware AI systems.

Abstract

Large Language Models (LLMs) are rapidly advancing across diverse domains, yet their application in theoretical physics remains inadequate. While current models show competence in mathematical reasoning and code generation, we identify critical gaps in physical intuition, constraint satisfaction, and reliable reasoning that cannot be addressed through prompting alone. Physics demands approximation judgment, symmetry exploitation, and physical grounding that require AI agents specifically trained on physics reasoning patterns and equipped with physics-aware verification tools. We argue that LLM would require such domain-specialized training and tooling to be useful in real-world for physics research. We envision physics-specialized AI agents that seamlessly handle multimodal data, propose physically consistent hypotheses, and autonomously verify theoretical results. Realizing this vision requires developing physics-specific training datasets, reward signals that capture physical reasoning quality, and verification frameworks encoding fundamental principles. We call for collaborative efforts between physics and AI communities to build the specialized infrastructure necessary for AI-driven scientific discovery.