Causal analysis – determining what causes what – is one of the most important yet technically demanding tasks in data science. Causal-Copilot (2025) is an LLM-powered autonomous agent that automates the entire causal analysis pipeline: from data ingestion and causal discovery through identification, estimation, and interpretation, all driven by natural language interaction.

Causal-Copilot operates through a modular pipeline where each stage is orchestrated by the LLM agent:

1. User Interaction: The user uploads data and specifies causal questions in natural language. The system parses queries, incorporates domain knowledge, and supports interactive feedback at every stage.

2. Preprocessing: Automatic data cleaning, schema extraction, and diagnostic analysis including tests for linearity, stationarity, and heterogeneity across subpopulations.

3. Algorithm Selection: The LLM evaluates data characteristics and selects from 20+ algorithms, then configures hyperparameters. This replaces the traditional expert-driven process of manually choosing between methods.

4. Core Analysis: Executes the selected algorithms for causal discovery, causal inference, and auxiliary analyses.

5. Postprocessing: Bootstrap evaluation for robustness, LLM-guided graph refinement, and support for user revisions to the causal graph.

6. Report Generation: Produces visualizations, natural language interpretations, and LaTeX reports.

Causal-Copilot integrates methods across the full spectrum of causal analysis:

Causal Discovery (Graph Structure Learning):

The NOTEARS optimization formulates DAG learning as a continuous problem:

$$\min_{W} \frac{1}{2n} \|X - XW\|_F^2 + \lambda \|W\|_1 \quad \text{s.t.} \quad h(W) = 0$$

where $h(W) = \text{tr}(e^{W \circ W}) - d$ is the acyclicity constraint.

Causal Inference (Effect Estimation):

• Double Machine Learning (DML)
• Doubly Robust estimation
• Instrumental Variables (IV, DRIV)
• Propensity Score Matching (PSM)
• Counterfactual estimation

Auxiliary Analysis:

• SHAP feature importance
• Anomaly attribution

class CausalCopilot:
    def __init__(self, llm, method_registry):
        self.llm = llm
        self.methods = method_registry
 
    def analyze(self, data, question):
        diagnostics = self.preprocess(data)
        selected_methods = self.select_algorithms(diagnostics, question)
        causal_graph = self.discover(data, selected_methods["discovery"])
        causal_graph = self.refine_graph(causal_graph, question)
        effects = self.estimate(
            data, causal_graph, 
            selected_methods["inference"],
            treatment=question.treatment,
            outcome=question.outcome
        )
        robust = self.bootstrap_evaluate(effects, n_iterations=500)
        report = self.generate_report(causal_graph, robust, question)
        return report
 
    def select_algorithms(self, diagnostics, question):
        prompt = self.build_selection_prompt(diagnostics, question)
        selection = self.llm.reason(prompt)
        return {
            "discovery": self.methods.get(selection.discovery_method),
            "inference": self.methods.get(selection.inference_method)
        }
 
    def discover(self, data, method):
        raw_graph = method.fit(data)
        bootstrap_graphs = [
            method.fit(data.sample(frac=0.8))
            for _ in range(100)
        ]
        edge_confidence = self.compute_edge_stability(bootstrap_graphs)
        return self.prune_unstable_edges(raw_graph, edge_confidence)
 
    def refine_graph(self, graph, question):
        refinement = self.llm.evaluate_graph(graph, question.domain)
        return graph.apply_refinements(refinement)

Causal-Copilot consistently outperforms individual algorithms across diverse scenarios:

Tabular Data (F1 Score):

Time Series Data (F1 Score):

The agent excels especially in challenging scenarios (extreme scale, non-Gaussian noise, heterogeneous domains) where algorithm selection is critical.

• Natural language interface: No statistical expertise required – users describe causal questions in plain English
• Automatic method selection: The LLM chooses appropriate algorithms based on data characteristics, eliminating the need for manual algorithm comparison
• Scalability: Handles datasets with up to 500 variables and complex time-series with long lags
• Robustness: Bootstrap evaluation and graph refinement ensure reliable results
• Interpretability: Generated reports explain findings in accessible language with supporting visualizations

• Causal-Copilot: An Autonomous Agent for End-to-End Causal Analysis (arXiv:2504.13263)
• Causal-Copilot Project Page

• Data Science Agents: DatawiseAgent
• Clinical Diagnosis Agents: MACD
• Knowledge Graph World Models: AriGraph