Publication
COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
David Steinmann; Antonia Wüst; Kristian Kersting; Wolfgang Stammer
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2606.28194, Pages 1-61, arXiv, 2026.
Abstract
Learning causal models from high-dimensional data is a significant challenge, particularly
in real-world settings where violations of core assumptions lead to causal identifiability
issues. Although massive amounts of prior knowledge are available, and contain valu-
able causal information, effectively integrating this knowledge into the causal discovery
process remains an open problem. We introduce CausalSTeward (CAST), a novel human-
in-the-loop framework for interactively assembling large causal models. CausalSteward
is a multi-agent collaborative system that tackles high-dimensional causality through a
divide-and-conquer approach where large clusters of variables are iteratively partitioned
and then separately analyzed. Our framework fuses prior knowledge with a data-driven
approach by using tailored tools such as retrieval augmented generation and conditional
independence tests. Finally, we use this work to examine the capabilities and limitations
of causal reasoning in multi-agent frameworks, and how the human-in-the-loop can con-
tribute to accurate and trustworthy results.