快讯
Collinear AI推出MatFlowBench：面向材料科学工作流的LLM智能体基准
Collinear AI发布MatFlowBench基准，用于评估运行材料科学工作流的LLM智能体。智能体需执行第一性原理计算或在预算限制下设计测量方案，并得出与所得数据相符、且满足任务所述物理假设的结论。
事件来源
查看原文
RT Collinear AI Introducing MatFlowBench, our benchmark for LLM agents running materials science workflows. Agents carry out first-principles calculations or design budget-limited measurement campaigns, then draw conclusions the resulting data support under the task’s stated physical assumptions. Website: http://www.matflowbench.com Blogpost: https://blog.collinear.ai/p/introducing-matflowbench