2606.08974v1 Jun 08, 2026 cs.AI

Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models

Yu Bai
Yu Bai
Beijing Academy of Artificial Intelligence (BAAI)
Citations: 286
h-index: 9
Xinyue Liang
Xinyue Liang
Citations: 30
h-index: 3
Yizhe Yang
Yizhe Yang
Citations: 150
h-index: 6
Bin Xu
Bin Xu
Citations: 116
h-index: 5
Jiawei Li
Jiawei Li
Citations: 130
h-index: 6
Yang Gao
Yang Gao
Citations: 55
h-index: 2

Large reasoning models (LRMs) have attracted increasing attention for their ability to solve complex mathematical problems by generating extended reasoning chains. In this work, we focus on two critical yet underexplored aspects of the reasoning process: reasoning transitions capturing the distinct transitions between reasoning steps and answer candidates reflecting the variety of solution paths produced by the model. We collectively define these two aspects as thinking schemata. We observe a correlation between the diversity of thinking schemata and model performance, which motivates us to enhance diversity as a means to further improve reasoning potential. To this end, we propose Diverse Schemata Policy Optimization (DiScO), a framework that first endows the model with schemata awareness, then encourages diversity through reinforcement learning, and further promotes diverse reasoning at inference time. Experiments on multiple mathematical reasoning benchmarks demonstrate that DiScO consistently outperforms standard group relative policy optimization. Beyond accuracy, human-annotated analyses show that DiScO substantially improves the model's ability to recover from erroneous initial attempts. Overall, our work suggests the important role that diversity of the thinking schemata plays and points to scaling along the diversity dimension as a promising research direction.

0 Citations
0 Influential
4.5 Altmetric
22.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!