A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hwang, Seonjeong, Seo, Jun, Kim, Hyounghun, Lee, Gary Geunbae
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916025629409280
author Hwang, Seonjeong
Seo, Jun
Kim, Hyounghun
Lee, Gary Geunbae
author_facet Hwang, Seonjeong
Seo, Jun
Kim, Hyounghun
Lee, Gary Geunbae
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19316
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
Hwang, Seonjeong
Seo, Jun
Kim, Hyounghun
Lee, Gary Geunbae
Computation and Language
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.
title A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
topic Computation and Language
url https://arxiv.org/abs/2605.19316