理论物理研究者终于有了一个能真正帮上忙的AI工具——physics-intern通过多智能体协作将难题拆解，效果远超单一模型。做科研自动化的团队值得关注这个框架的设计思路。
David Louapre 发布了 physics-intern，一个专为理论物理设计的智能体框架。该框架将复杂物理问题分解并分配给多个专业智能体协同解决，包括自我纠错、推导方程、计算中间结果和重新评估最佳方法。在 CritPt 基准测试上，physics-intern 将 Gemini 3.1 Pro 的性能从 17.7% 提升至 31.4%，达到新的最优水平。这展示了多智能体协作在解决高难度科研问题上的巨大潜力。
watching a team of agents tackling a hard theoretical physics problem is quite mesmerizing - self-co...
watching a team of agents tackling a hard theoretical physics problem is quite mesmerizing - self-correcting, deriving hard equations, computing intermediate results, re-estimating the best approach Your browser does not support the video tag. 🔗 View on Twitter David Louapre @dlouapre Meet physics-intern🧑🎓, our agentic framework for theoretical physics. It takes Gemini 3.1 Pro from 17.7% to 31.4% on CritPt, a new SOTA on one of the hardest benchmarks for LLMs. Theoretical physics is hard for humans and LLMs alike. But physics-intern decomposes problems and dispatches them to a team of specialized agents, solving research-level questions far more effectively than the base model alone. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 11 🔄 27 ❤️ 158 👀 30148 📊 32 ⚡