Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2602.11527 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914324259274752 |
|---|---|
| author | Zhu, Jiawei Chen, Wei Cai, Ruichu |
| author_facet | Zhu, Jiawei Chen, Wei Cai, Ruichu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11527 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CausalAgent: A Conversational Multi-Agent System for End-to-End Causal Inference Zhu, Jiawei Chen, Wei Cai, Ruichu Artificial Intelligence 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. |
| title | CausalAgent: A Conversational Multi-Agent System for End-to-End Causal Inference |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.11527 |