# ORCA: ORchestrating Causal Agent

## TL;DR

ORCA is a multi-agent framework that enhances causal analysis on relational databases by maintaining shared state and human checkpoints, leading to more accurate and efficient analysis compared to baseline LLM assistants.

## Contribution

It introduces a novel multi-agent system with shared state and human checkpoints to improve the coherence and reliability of causal analysis workflows.

## Key findings

- Participants using ORCA completed analysis 42% more often than baseline.
- ORCA reduced time spent on data exploration and query refinement by 76%.
- ORCA achieved lower average treatment effect (ATE) error.

## Abstract

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.