rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

arxiv:2501.04519

Original source · Paper JSON

Reasoning and the "physics" of language models · 2025-01-08

Cites (2) · Cited by (2)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3
4. Part 4

Contents

• rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
• Abstract
• 1 Introduction
• 2 Related Works
• 3 Methodology
• 3.1 Design Choices
• 3.2 Step-by-Step Verified Reasoning Trajectory
• 3.3 Process Preference Model
• 3.4 Self-Evolved Deep Thinking
• 3.4.1 Training with Step-by-Step Verified Reasoning Trajectory
• 3.4.2 Recipe for Self-Evolution
• 4 Evaluation
• 4.1 Setup
• 4.2 Main Results
• 4.3 Ablation Study and Analysis
• 5 Findings and Discussions
• 6 Conclusion
• Acknowledgement
• Appendix A Appendix
• A.1 Additional Experiments and Details
• A.2 Examples of Reasoning Trajectories
• A.3 Prompt Examples
• Instructions for reporting errors