AI 代理在国际物理奥赛中得分超人类金牌选手平均水平
Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025
- 构建集成物理规律的智能体系统，通过工具调用解决复杂物理问题
- 在2025年IPhO理论题中获23.5/30分，排名前14%，超越金牌选手均值
- 适合对通用人工智能、科学推理感兴趣的科研人员和开发者
物理学提供描述和预测自然世界的基本规律。追求更通用、真实世界智能的AI系统必须具备强大的物理问题求解能力：即能够建立并应用物理定律来解释和预测物理过程。国际物理奥林匹克（IPhO）——全球最负盛名的物理竞赛——为此提供了严格的评估基准。我们提出Physics Supernova，一个具备卓越物理问题求解能力的AI代理系统，在2025年IPhO理论题中获得23.5/30分，排名406名参赛者中的第14位，超越人类金牌选手的平均表现。我们对Physics Supernova在多种物理任务中的能力与灵活性进行了深入分析。结果表明，原则性地整合工具到代理系统中，可在解决复杂科学问题时带来显著性能提升。代码已开源：https://github.com/CharlesQ9/Physics-Supernova。
原文摘要 · Abstract (English)
Physics provides fundamental laws that describe and predict the natural world. AI systems aspiring toward more general, real-world intelligence must therefore demonstrate strong physics problem-solving abilities: to formulate and apply physical laws for explaining and predicting physical processes. The International Physics Olympiad (IPhO)--the world's most prestigious physics competition--offers a rigorous benchmark for this purpose. We introduce Physics Supernova, an AI agent system with superior physics problem-solving abilities that match elite IPhO gold medalists. In IPhO 2025 theory problems, Physics Supernova attains 23.5/30 points, ranking 14th of 406 contestants and surpassing the median performance of human gold medalists. We extensively analyzed Physics Supernova's capabilities and flexibility across diverse physics tasks. These results show that principled tool integration within agent systems can deliver competitive improvements in solving challenging science problems. The codes are available at https://github.com/CharlesQ9/Physics-Supernova.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。