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

Jul 17, 2026

CIPHER is a new automated data science agent that improves test-time scaling by decoupling the generation of candidate initial states from their strategic selection for parallel execution. In evaluations on both closed-form and open-form data science tasks, CIPHER outperforms state-of-the-art models in matched-model comparisons and remains competitive with larger models despite using a smaller base language model. The study also analyzes how different design choices in the framework affect performance and provides actionable recommendations for practitioners.

Why it matters: This work introduces a principled approach to test-time scaling for AI agents, addressing cascading errors from suboptimal initial states and offering practical guidance for building more robust data science automation.

Full story at: arXiv AI/ML ↗