Structured knowledge-based causal discovery: Agentic streams of thought

Abstract

Causal discovery—the systematic identification of cause-and-effect relationships among variables—forms the cornerstone of causal inference. Its application enables reliable predictions and targeted interventions across complex systems, from medical treatments to engineering processes. Traditional statistical causal discovery methods face significant limitations with high-dimensional data structures, while existing knowledge-based approaches rely on single large-scale models that raise fundamental concerns about computational efficiency and result reliability. The Agentic Stream of Thought (ASoT) addresses these limitations through a novel architecture that orchestrates multiple smaller open-source language models. The framework integrates hierarchical query decomposition with Model Compiler refinement, while dual-stream thought processing enables balanced analysis through parallel evaluation of competing hypotheses. Dedicated Direction and Transitive Processors enhance reasoning by resolving bidirectional relationships and refining transitive pathways. A two-tiered quality gate system and complementary consensus mechanisms—Delphi protocol and Ensemble Synthesis Method—iteratively refine outputs while mitigating hallucination risks. Empirical evaluations across causal discovery benchmarks and question-answering tasks demonstrate that this approach matches or exceeds state-of-the-art models while enabling local deployment, establishing that sophisticated orchestration of smaller models provides a more sustainable path than increasing model scale alone.