CausalAgent: A Conversational Multi-Agent System for End-to-End Causal Inference

TL;DR

CausalAgent is an innovative conversational multi-agent system that automates end-to-end causal inference, making complex analysis accessible through natural language interaction and visualizations, thereby lowering technical barriers.

Contribution

It introduces a novel multi-agent framework integrating RAG and MCP for automated, user-friendly causal inference from data to report generation.

Findings

Automates data cleaning and causal structure learning

Enables natural language interaction for analysis questions

Provides interactive visualizations for interpretability

Abstract

Causal inference holds immense value in fields such as healthcare, economics, and social sciences. However, traditional causal analysis workflows impose significant technical barriers, requiring researchers to possess dual backgrounds in statistics and computer science, while manually selecting algorithms, handling data quality issues, and interpreting complex results. To address these challenges, we propose CausalAgent, a conversational multi-agent system for end-to-end causal inference. The system innovatively integrates Multi-Agent Systems (MAS), Retrieval-Augmented Generation (RAG), and the Model Context Protocol (MCP) to achieve automation from data cleaning and causal structure learning to bias correction and report generation through natural language interaction. Users need only upload a dataset and pose questions in natural language to receive a rigorous, interactive analysis report. As a novel user-centered human-AI collaboration paradigm, CausalAgent explicitly models the analysis workflow. By leveraging interactive visualizations, it significantly lowers the barrier to entry for causal analysis while ensuring the rigor and interpretability of the process.