CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents

2026-10-27 · ArXiv

arXiv:2607.14386v2 Announce Type: replace

Abstract: Enterprise data science and analytics spans closed-ended information extraction with verifiable answers and open-ended insight discovery. Agents are evaluated on one or the other, so there is no evidence on whether one system can serve both. We present \texttt{CIPHER}, a data science agent built on a Decoupled Exploration--Selection (DES) framework that applies test-time scaling at the plan level: generating $N$ candidate analysis plans, selecting $M{

原文链接：https://arxiv.org/abs/2607.14386

查看更多资讯请见 AI 行业资讯。