AGISystem2 Research

Causal Inference

Theoretical frameworks for modeling structural mechanisms and counterfactual reasoning.

The Ladder of Causation

Causal Inference, developed extensively by Judea Pearl, transitions machine learning from statistical curve-fitting (correlations) to the modeling of underlying mechanisms (causality).

Levels of Causal Reasoning

  1. Association: Identifying statistical relationships between variables (typical of standard neural networks).
  2. Intervention: Predicting the effects of direct changes to a system (modeled via the do-calculus).
  3. Counterfactuals: Retrospective analysis of specific outcomes to determine the influence of alternate actions ("What if I had acted differently?").

Historical & Alternative Methods

Technical Objective

Standard LLMs operate primarily at the level of association. The integration of Structural Causal Models (SCMs) enables agents to predict action consequences and provide mechanistic explanations for their decision-making processes based on cause-effect relationships.

Libraries & Links