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.

翻译：大型语言模型（LLM）正在众多领域快速发展，但其在理论物理中的应用仍显不足。尽管当前模型在数学推理和代码生成方面展现出一定能力，我们发现了其在物理直觉、约束满足和可靠推理方面存在关键缺陷，这些缺陷无法仅通过提示工程解决。物理学需要近似判断、对称性利用和物理基础，这要求AI智能体必须经过专门针对物理推理模式的训练，并配备具备物理感知能力的验证工具。我们认为，LLM需要此类领域专门化的训练和工具支持，方能在真实世界的物理研究中发挥作用。我们设想一种专门面向物理学的AI智能体，能够无缝处理多模态数据、提出物理一致的假设，并自主验证理论结果。实现这一愿景需要开发物理学专用的训练数据集、能够捕捉物理推理质量的奖励信号，以及编码基本原理的验证框架。我们呼吁物理学与人工智能学界开展合作，共同构建AI驱动科学发现所必需的专门化基础设施。