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

2026-02-12

AI Summary

This work proposes a natural language–driven multi-agent system that automates end-to-end causal inference—from data preprocessing and causal structure learning to bias correction and report generation—thereby addressing the high technical barriers of traditional workflows, which demand advanced statistical and programming expertise alongside tedious manual intervention. By integrating a multi-agent architecture (MAS), retrieval-augmented generation (RAG), and the Model Context Protocol (MCP), the system establishes a user-centered human-AI collaboration paradigm. It explicitly models the analytical pipeline and incorporates interactive visualizations to preserve methodological rigor and interpretability while drastically lowering accessibility thresholds. Users need only upload their data and pose queries in natural language to receive trustworthy, interactive causal analysis reports, significantly enhancing both usability and efficiency.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Multiagent Systems: Modeling other Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• causal inference
• technical barriers
• workflow complexity
• accessibility
• manual analysis

Innovation

• Multi-Agent Systems
• Retrieval-Augmented Generation
• Causal Inference
• Model Context Protocol
• Conversational AI