PhysMaster：构建一个自主的AI物理学家用于理论和计算物理学研究
PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
AI总结：
PhysMaster通过结合抽象推理与数值计算，利用LANDAU数据宇宙提升决策可靠性，实现理论与计算物理学研究的自动化与自主发现。
摘要：
在LLM进步的推动下，产生了具备与人类科学家相当知识和操作能力的代理，暗示其可能协助、加速和自动化研究。然而，现有研究主要在定义明确的基准或一般任务如文献检索上评估这些系统，限制了其在开放科学场景中的端到端问题解决能力。这在物理学中尤为明显，因为物理学抽象、数学密集且需要将分析推理与基于代码的计算相结合。为此，我们提出了PhysMaster，一个基于LLM的代理，充当自主的理论和计算物理学家。PhysMaster将抽象推理与数值计算相结合，并利用LANDAU，即分层学术数据宇宙，该数据宇宙保存了检索到的文献、整理的先前知识和已验证的方法学轨迹，从而增强决策的可靠性和稳定性。它还采用了一种自适应探索策略，平衡效率和开放探索，使其在超长时间范围任务中表现出鲁棒性。我们评估了PhysMaster在高能理论、凝聚态理论到天体物理学中的问题，包括：(i) 加速，将劳动密集型研究从几个月缩短到几小时；(ii) 自动化，自主执行假设驱动的循环；(iii) 自主发现，独立探索开放性问题。
英文摘要：
Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires deep domain expertise, long-horizon reasoning, and reliable numerical computation. We introduce PRL-Bench, a research-reproduction benchmark adapted from 100 Physical Review Letters papers across major areas of modern physics. PRL-Bench distills realistic research workflows into traceable tasks with explicit intermediate artifacts and diverse evaluation rubrics; each task is estimated by domain experts to require more than six hours for a specialized PhD student to reproduce independently. Evaluations show that existing agents remain unreliable on extended research workflows. We therefore present PhysMaster, a scientific agent combining adaptive MCTS-based multi-trajectory exploration with hierarchical memory to improve long-horizon robustness and knowledge accumulation. PhysMaster achieves the highest overall PRL-Bench score of 51.08, outperforming Codex, OpenHands, OpenClaw, and ReAct, and yields relative improvements of 14.13 percent to 93.38 percent across backbone models. Error analysis shows that PhysMaster substantially reduces failures from incomplete long-horizon execution, while remaining bottlenecks lie in physics knowledge and analytical reasoning. Together, PRL-Bench and PhysMaster provide a rigorous benchmark and effective system for advancing autonomous AI research in frontier physics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
