A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
For educators and test developers, this provides a more reliable method for generating reading comprehension items with precise difficulty levels, addressing a key limitation of existing single-agent approaches.
MAFIG, a multi-agent framework using LLMs and feature-specific evaluators, generates reading comprehension items that adhere to target difficulty constraints at a significantly higher rate than single-agent baselines, enabling robust difficulty control.
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 introduce MAFIG, a Multi-agent Framework for Feature-constrained Item Generation, where multiple LLM agents and feature-specific evaluators collaborate to generate and iteratively revise items based on intended constraints. Furthermore, to verify the efficacy of MAFIG in difficulty control, we propose a method for constructing a sequence of feature constraint sets that yield items with monotonically increasing difficulty. Experimental results demonstrate that MAFIG generates items that adhere to target constraints at a significantly higher rate than baselines, achieving robust difficulty control through the difficulty-calibrated constraint sequence.