Watching a Team of Agents Tackle Theoretical Physics Is Mesmerizing – Physics-Intern Breaks New Ground
Thomas Wolf(@Thom_Wolf)177 字 (约 1 分钟)
78
The Physics-Intern framework boosts Gemini 3.1 Pro's performance on the CritPt benchmark from 17.7% to 31.4% via multi-agent collaboration, setting a new SOTA in theoretical physics reasoning.
入选理由：Physics-Intern 使用多智能体协作框架解决复杂理论物理问题。
FeaturedTweet#AI Agent#Theoretical Physics#LLM Reasoning#Gemini#CritPt中英混合