Papers
arxiv:2507.13266

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Published on Jul 17
Authors:
,
,
,
,
,
,

Abstract

Question Augmentation during reinforcement learning training enhances multi-step reasoning in large language models, particularly on math problems, by introducing partial solutions and improving sample efficiency.

AI-generated summary

Reinforcement learning (RL) has become a key component in training large language reasoning models (LLMs). However, recent studies questions its effectiveness in improving multi-step reasoning-particularly on hard problems. To address this challenge, we propose a simple yet effective strategy via Question Augmentation: introduce partial solutions during training to reduce problem difficulty and provide more informative learning signals. Our method, QuestA, when applied during RL training on math reasoning tasks, not only improves pass@1 but also pass@k-particularly on problems where standard RL struggles to make progress. This enables continual improvement over strong open-source models such as DeepScaleR and OpenMath Nemotron, further enhancing their reasoning capabilities. We achieve new state-of-the-art results on math benchmarks using 1.5B-parameter models: 67.1% (+5.3%) on AIME24, 59.5% (+10.0%) on AIME25, and 35.5% (+4.0%) on HMMT25. Further, we provide theoretical explanations that QuestA improves sample efficiency, offering a practical and generalizable pathway for expanding reasoning capability through RL.

Community

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.13266 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.