AI RESEARCH
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
arXiv CS.CL
•
ArXi:2605.19316v1 Announce Type: new Recent studies in difficulty-controlled reading comprehension item generation have leveraged large language models (LLMs) to produce items by adjusting difficulty-related features. However, existing methods typically rely on a single-agent prompting approach, which often fails to consistently satisfy specified feature constraints, resulting in items that deviate from the target difficulty level. To address this limitation, we