两篇新研究论文探讨了在科学发现中使用AI代理，特别是在物理学和计算数学领域。第一篇论文介绍了StatMechBench-v0，这是一个旨在测试AI代理在物理问题中识别统计力学映射能力的基准，揭示了当前LLM在数值一致性之外的推理局限性。第二篇论文提出了EvoPINN，一个使用LLM为物理信息神经网络（PINNs）发现可执行算法的代理框架，展示了显著的误差减少和一种称为SLRC-PINN的新型架构的发明。 AI
影响 这些进展表明，AI代理可以通过自动化复杂问题的解决和专业领域的算法发现来加速科学突破。
排序理由 两篇发表在arXiv上的学术论文，详细介绍了AI在科学发现中的新应用。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.26367v1 Announce Type: new Abstract: An important skill in theoretical physics is to recognize when a new problem can be transformed into a known model. We study this skill as an AI-agent task: can LLM-based agents discover statistical mechanical mappings from a raw pa…
arXiv:2607.26490v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representati…
Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies on the manual, trial-and-error engineering of neural representations, loss formulations, and optimization dynamics.…