CIPHER：用于数据科学智能体测试时扩展的解耦探索-选择框架

中文摘要 AI 辅助

数据科学任务从封闭式信息提取到开放式分析，给自动化带来重大挑战。由语言模型驱动的近期人工智能智能体有望处理此类复杂任务。但现有智能体通常依赖单个初始状态，易受次优初始状态引发的级联错误影响。为缓解此问题，我们提出CIPHER，一种通过生成和选择多个初始状态进行并发执行来利用测试时扩展的自动化数据科学智能体。与现有关于人工智能智能体测试时扩展的工作不同，CIPHER明确将候选初始状态的生成与其并行执行的策略选择解耦。通过在两个基准（封闭式和开放式任务）上的广泛评估，我们证明CIPHER在匹配模型比较中超过了现有技术水平，并且尽管依赖小得多的基础语言模型，与更大模型基线相比仍具有竞争力。我们的实证研究刻画了解耦探索-选择（DES）框架的设计空间：量化了生成策略、选择策略和聚合器模型能力如何对整体性能做出贡献，并为从业者得出可操作的设计建议。

英文摘要

Data science tasks span from closed-ended information extraction to open-ended analysis, presenting significant challenges for automation. Recent AI agents powered by language models show promise for handling such complex tasks. However, existing agents typically rely on a single initial state that conditions the entire agent's execution, making them vulnerable to cascading errors initiated by a suboptimal initial state. To mitigate this, we present CIPHER, an automated data science agent that leverages test-time scaling through the generation and selection of multiple initial states for concurrent execution. Unlike existing works on test-time scaling of AI agents, CIPHER explicitly decouples the generation of candidate initial states from their strategic selection for parallel execution. Through extensive evaluation on two benchmarks (closed-form and open-form tasks), we demonstrate that CIPHER exceeds state-of-the-art performance in matched-model comparisons, and remains competitive against larger-model baselines despite relying on a substantially smaller base LM. Our empirical study characterizes the design space of the Decoupled Exploration-Selection (DES) framework: we quantify how generation strategy, selection strategy, and aggregator model capacity contribute to overall performance, and derive actionable design recommendations for practitioners.

发表机构

• Amazon Web Services（亚马逊网络服务公司）

机构由 AI 辅助整理，请以论文原文为准。