Large Reasoning Models (LRMs) benefit substantially from training on challenging competition-level questions. However, existing automated question synthesis methods lack precise difficulty control, incur high computational costs, and struggle to generate competition-level questions at scale. In this paper, we propose CoDiQ (Controllable Difficult Question Generation), a novel framework enabling fine-grained difficulty control via test-time scaling while ensuring question solvability. Specifically, first, we identify a test-time scaling tendency (extended reasoning token budget boosts difficulty but reduces solvability) and the intrinsic properties defining the upper bound of a model's ability to generate valid, high-difficulty questions. Then, we develop CoDiQ-Generator from Qwen3-8B, which improves the upper bound of difficult question generation, making it particularly well-suited for challenging question construction. Building on the CoDiQ framework, we build CoDiQ-Corpus (44K competition-grade question sequences). Human evaluations show these questions are significantly more challenging than LiveCodeBench/AIME with over 82% solvability. Training LRMs on CoDiQ-Corpus substantially improves reasoning performance, verifying that scaling controlled-difficulty training questions enhances reasoning capabilities. We open-source CoDiQ-Corpus, CoDiQ-Generator, and implementations to support related research.
Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting
Tencent Jarvis Lab(腾讯天衍实验室);Carnegie Mellon University(卡内基梅隆大学);Université de Montréal(蒙特利尔大学);Peking University(北京大学);The University of Sheffield(谢菲尔德大学)
Graduate School of Artificial Intelligence, POSTECH, South Korea(韩国立科学技术院人工智能研究生院);Department of Computer Science and Engineering, POSTECH, South Korea(韩国立科学技术院计算机科学与工程系);Mila Quebec AI Institute, Canada(魁北克AI研究院);McGill University, Canada(麦吉尔大学)
LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translation
School of Informatics, Xiamen University(厦门大学信息学院);School of Journalism and Communication, Xiamen University(厦门大学新闻传播学院);School of Film, Xiamen University(厦门大学电影学院);Xiamen Key Laboratory of Intelligent Storage and Computing, Xiamen University(厦门大学智能存储与计算重点实验室);Institute of Artificial Intelligence, Xiamen University(厦门大学人工智能研究院)
CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RL
Tsinghua University(清华大学);Beihang University(北京航空航天大学);Southern University of Science and Technology(南方科技大学);Renmin University of China(中国人民大学);Shanghai University of Finance and Economics(上海财经大学)