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

arXiv: https://arxiv.org/abs/2605.19316 · HTML: https://mlsanity.com/paper/2605.19316/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 38 references that are in the map.
- First posted on arXiv 19 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling](https://mlsanity.com/paper/2502.17651/) (2025)
- [Zero-Shot Strategies for Length-Controllable Summarization](https://mlsanity.com/paper/2501.00233/) (2024)
- [Assessing AI-Generated Questions' Alignment with Cognitive Frameworks in Educational Assessment](https://mlsanity.com/paper/2504.14232/) (2025)
- [Question Difficulty Ranking for Multiple-Choice Reading Comprehension](https://mlsanity.com/paper/2404.10704/) (2024)
- [Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items?](https://mlsanity.com/paper/2510.25064/) (2025)
- [KAQG: A Knowledge-Graph-Enhanced RAG for Difficulty-Controlled Question Generation](https://mlsanity.com/paper/2505.07618/) (2025)

## Abstract (arXiv)

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.