Causal-Copilot: An Autonomous Causal Analysis Agent

TL;DR

Causal-Copilot addresses the gap between advanced causal analysis methods and real-world deployment by introducing an LLM-driven autonomous agent that can automatically perform causal discovery, inference, parameter tuning, and results interpretation for both tabular and time-series data. The system integrates over 20 state-of-the-art methods across constraint-based, score-based, MB-based, and hybrid families, coordinated by a central reasoning layer and supported by a knowledge memory. Empirical results show superior performance and robustness across a variety of data conditions, including heterogeneous domains, missing data, and noise, demonstrating the approach's scalability and practicality. The work advances accessible, interpretable, and extensible causal analysis workflows, enabling domain experts to leverage sophisticated causal tools with minimal specialized training and offering a live demo and downloadable reports for real-world workflows.

Abstract

Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algorithmic complexity. This disconnect between causal methodology and practical usability presents a dual challenge: domain experts are unable to leverage recent advances in causal learning, while causal researchers lack broad, real-world deployment to test and refine their methods. To address this, we introduce Causal-Copilot, an autonomous agent that operationalizes expert-level causal analysis within a large language model framework. Causal-Copilot automates the full pipeline of causal analysis for both tabular and time-series data -- including causal discovery, causal inference, algorithm selection, hyperparameter optimization, result interpretation, and generation of actionable insights. It supports interactive refinement through natural language, lowering the barrier for non-specialists while preserving methodological rigor. By integrating over 20 state-of-the-art causal analysis techniques, our system fosters a virtuous cycle -- expanding access to advanced causal methods for domain experts while generating rich, real-world applications that inform and advance causal theory. Empirical evaluations demonstrate that Causal-Copilot achieves superior performance compared to existing baselines, offering a reliable, scalable, and extensible solution that bridges the gap between theoretical sophistication and real-world applicability in causal analysis. A live interactive demo of Causal-Copilot is available at https://causalcopilot.com/.

Figures (43)

• Figure 1: The overall architecture of our Causal-Copilot.
• Figure 2: The overall workflow of our Causal-Copilot, with an example of discovering the causal structure in collected advertising related data.
• Figure 3: The website demo of our Causal-Copilot.
• Figure 4: Performance vs. sample size for tabular causal discovery algorithms. Only the top 10 algorithms with the highest average F1 scores are shown. 'L' and 'NL' indicate results on linear and non-linear data, respectively.
• Figure 5: Performance vs. edge probability for tabular causal discovery algorithms. Only the top 10 algorithms with the highest average F1 scores are shown. 'L' and 'NL' indicate results on linear and non-linear data, respectively.