Causal analysis on relational databases is challenging, as analysis datasets must be repeatedly queried from complex schemas. Recent LLM systems can automate individual steps, but they hardly manage dependencies across analysis stages, making it difficult to preserve consistency between causal hypothesis. We propose ORCA (ORchestrating Causal Agent), an interactive multi-agent framework to enable coherent causal analysis on relational databases by maintaining shared state and introducing human checkpoints. In a controlled user study, participants using ORCA successfully completed end-to-end analysis more often than with a baseline LLM (GPT-4o-mini) assistant by 42 percentage points, achieved substantially lower ATE error, and reduced time spent on repetitive data exploration and query refinement by 76\% on average. These results show that ORCA improves both how users interact with the causal analysis pipeline and the reliability of the resulting causal conclusions.

翻译：关系数据库上的因果分析具有挑战性，因为分析数据集必须从复杂的数据库模式中重复查询。近期的大型语言模型系统能够自动化个别步骤，但它们难以管理分析阶段间的依赖关系，导致难以保持因果假设间的一致性。我们提出ORCA（因果分析智能体编排框架），这是一个交互式多智能体框架，通过维护共享状态并引入人工检查点，实现在关系数据库上进行连贯的因果分析。在一项受控用户研究中，使用ORCA的参与者成功完成端到端分析的频率比使用基线大型语言模型（GPT-4o-mini）助手高出42个百分点，获得了显著更低的平均处理效应误差，并将重复性数据探索和查询优化所花费的时间平均减少了76%。这些结果表明，ORCA既改善了用户与因果分析流程的交互方式，也提高了最终因果结论的可靠性。