This paper introduces Epi2Diff, a framework that uses Large Language Model reasoning steps to predict how difficult an educational assessment item will be for humans, offering a new way to understand problem-solving processes.

In plain terms

Predicting how difficult a test question, or "item," will be for humans is crucial for creating fair and effective educational assessments. Existing methods often rely on expensive human trials or simply analyzing the question's text, which doesn't explain *why* an item is hard. The researchers developed Epi2Diff, a framework that uses the step-by-step thinking processes, called "reasoning traces," generated by advanced AI models (Large Reasoning Models or LRMs) when they attempt to solve a problem. Epi2Diff breaks these traces into "cognitive episodes," which are distinct stages of problem-solving like understanding or planning. By analyzing the flow, complexity, and transitions between these episodes, Epi2Diff creates unique features that predict human item difficulty more accurately. They found that Epi2Diff consistently outperformed other methods, showing that harder items lead to more iterative and complex AI reasoning, not just longer answers.