贝叶斯实验设计让LLM实验次数减少约5倍
Letting an LLM decide what to try next wastes experiments, and this paper shows…
Letting an LLM decide what to try next wastes experiments, and this paper shows that scoring its ideas with standard Bayesian math cuts the count roughly 5×.
让LLM决定下一步尝试什么会浪费实验，这篇论文表明，用标准贝叶斯数学对其想法进行评分可将实验次数大约减少5倍。
The system is called Model Discovery Agent, or MDA. The LLM suggests possible explanations for the data, and MDA picks the one experiment that would best tell those explanations apart.
该系统称为模型发现代理（MDA）。LLM提出数据可能的解释，MDA则挑选最能区分这些解释的一个实验。
Nothing gets spent on experiments that only confirm what it already believes.
不会在仅确认其已有信念的实验上花费任何资源。
On a physics benchmark, MDA's model was accurate enough to pass on 93% of runs. The same LLM working alone passed 31%. MDA also matched a published result using 8 experiments instead of about 41.
在物理基准测试中，MDA的模型足够准确，在93%的运行中通过。同一LLM单独运行时通过率为31%。MDA还匹配了已发表的结果，仅用8次实验而非约41次。
alphaxiv .org/pdf/2608.09696v3
alphaxiv .org/pdf/2608.09696v3
"M ODEL D ISCOVERY AGENT: LLM- ASSISTED B AYESIAN EXPERIMENT DESIGN"
“模型发现代理：LLM辅助的贝叶斯实验设计”
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力