Researchers introduced Learning-to-Theorize, a new learning paradigm for inferring explicit explanatory theories of the world from raw observations. This approach uses a Neural Theorizer (NEO) to induce latent programs as a learned Language of Thought, enabling explanation-driven generalization. This development may impact AI agents by providing a new framework for understanding the world and generating explanations.

A new framework for probabilistic explainability is proposed, using sparse, anchored linear models for both classification and regression tasks. This approach generalizes subset-based methods and provides a sparsity budget, making it useful for understanding AI model decisions.