Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2606.08974v1
• Date: Mon, 08 Jun 2026 03:17:31 GMT
• Title: Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models
• Abstract summary: We focus on two critical yet underexplored aspects of the reasoning process.<n>We observe a correlation between the diversity of thinking schemata and model performance.<n>We propose Diverseta Policy Optimization (DiScO), a framework that first endows the model with schemata awareness.
• Score: 24.185783626370213
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning [61.60016491769943]
  In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding.<n>We propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI) with a stage-wise preference training strategy.<n>Experiments across multiple model scales and families demonstrate consistent improvements, even surpassing larger open-source models.
  arXiv  Detail & Related papers  (2026-08-27T03:24:03Z)
• Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization [89.68681087743876]
  Multimodal Large Language Models (MLLMs) have incentivized models to think with images'' by actively invoking visual tools during multi-turn reasoning.<n>The common Reinforcement Learning practice of relying on outcome-based rewards ignores the fact that textual plausibility often masks executive failure.<n>We introduce Multimodal Agentic Policy Optimization (MAPO), bridging the gap between textual reasoning and visual actions generated by models within their Multimodal Chain-of-Thought.
  arXiv  Detail & Related papers  (2026-04-08T07:48:07Z)
• Learning Structured Reasoning via Tractable Trajectory Control [99.75278337895024]
  Ctrl-R is a framework for learning structured reasoning via tractable trajectory control.<n>We show that Ctrl-R enables effective exploration and internalization of previously unattainable reasoning patterns.
  arXiv  Detail & Related papers  (2026-03-02T09:18:19Z)
• SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning [50.93295951454092]
  We introduce a set level diversity objective defined over sampled trajectories using kernelized similarity.<n>Our approach derives a leave-one-out marginal contribution for each sampled trajectory and integrates this objective as a plug-in advantage shaping term for policy optimization.<n>Experiments across a range of model scales demonstrate the effectiveness of our proposed algorithm, consistently outperforming strong baselines in both Pass@1 and Pass@K across various benchmarks.
  arXiv  Detail & Related papers  (2026-02-01T07:13:20Z)
• Reasoning Models Generate Societies of Thought [9.112083442162671]
  We show that enhanced reasoning emerges from simulating multi-agent-like interactions.<n>We find that reasoning models like DeepSeek-R1 and QwQ-32B exhibit much greater perspective diversity than instruction-tuned models.
  arXiv  Detail & Related papers  (2026-01-15T19:52:33Z)
• Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models [28.756240721942138]
  Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning.<n>We propose Thinking with Nothinking (JointThinking), a new ICL paradigm that prompts the model to generate two answers in parallel.<n>JointThinking significantly outperforms few-shot chain-of-thought (CoT), thinking twice and majority voting.
  arXiv  Detail & Related papers  (2025-08-05T12:09:55Z)
• Diversity-Enhanced Reasoning for Subjective Questions [24.896059589693607]
  MultiRole-R1, a diversity-enhanced training framework, synthesizes reasoning chains incorporating various role perspectives.<n>It increases the in-domain and out-of-domain accuracy by 14.1% and 7.64%, and even enhances the performance on advanced math reasoning such as AIME 2024.
  arXiv  Detail & Related papers  (2025-07-27T09:07:42Z)
• Multimodal Mathematical Reasoning with Diverse Solving Perspective [65.07953438724105]
  We introduce MathV-DP, a novel dataset that captures multiple diverse solution trajectories for each image-question pair.<n>We propose Qwen-VL-DP, a model built upon Qwen-VL, fine-tuned with supervised learning and enhanced via group relative policy optimization.<n>Our method emphasizes learning from varied reasoning perspectives and distinguishing between correct yet distinct solutions.
  arXiv  Detail & Related papers  (2025-07-03T17:07:20Z)
• From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models [10.38327947136263]
  This paper proposes a novel framework for analyzing the reasoning characteristics of four cutting-edge large reasoning models.<n>A diverse dataset consists of real-world scenario-based questions covering logical deduction, causal inference, and multi-step problem-solving.<n>The research results uncover various patterns of how these models balance exploration and exploitation, deal with problems, and reach conclusions.
  arXiv  Detail & Related papers  (2025-06-20T14:02:16Z)
• Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization [14.346638764967357]
  Multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks.<n>We propose Evolution of Thought (EoT) to foster both high-quality and diverse reasoning paths.<n>We show EoT achieves superior reasoning performance and efficiency compared to other competitive baselines.
  arXiv  Detail & Related papers  (2024-11-24T14:59:30Z)
• Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training [49.3242278912771]
  Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework. We propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process.
  arXiv  Detail & Related papers  (2023-11-23T17:09:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.