arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.01660cs.CLcs.AI
收藏

CoDiQ:测试时缩放用于可控的困难问题生成

CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation

Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院)

Zhongyuan Peng, Caijun Xu, Changyi Xiao, Shibo Hong, Eli Zhang, Stephen Huang, Yixin Cao

AI总结:

CoDiQ通过测试时缩放实现可控困难问题生成,提升模型推理能力。

摘要:

大型推理模型(LRMs)显著受益于在具有挑战性的竞赛级问题上进行训练。然而,现有的自动问题合成方法缺乏精确的难度控制,计算成本高,并且难以在大规模上生成竞赛级问题。在本文中,我们提出了CoDiQ(可控困难问题生成),一种新的框架,通过测试时缩放实现细粒度的难度控制,同时确保问题的可解性。具体来说,首先,我们识别出测试时缩放倾向(扩展推理标记预算会增加难度但降低可解性)以及定义模型生成有效高难度问题上限的内在属性。然后,我们从Qwen3-8B开发了CoDiQ-Generator,它提高了困难问题生成的上限,使其特别适合挑战性问题的构建。基于CoDiQ框架,我们构建了CoDiQ-Corpus(44K个竞赛级问题序列)。人类评估显示这些问题比LiveCodeBench/AIME更具挑战性,超过82%的问题可解。在CoDiQ-Corpus上训练LRMs显著提高了推理性能,验证了缩放受控难度训练问题能增强推理能力。我们开源了CoDiQ-Corpus、CoDiQ-Generator和实现以支持相关研究。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑