| Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning | May 26, 2025 | DiversityMath | —Unverified | 0 |
| Improving Multilingual Math Reasoning for African Languages | May 26, 2025 | MathMathematical Reasoning | —Unverified | 0 |
| The Role of Diversity in In-Context Learning for Large Language Models | May 26, 2025 | DiversityIn-Context Learning | —Unverified | 0 |
| Interleaved Reasoning for Large Language Models via Reinforcement Learning | May 26, 2025 | Logical ReasoningMath | —Unverified | 0 |
| Faster and Better LLMs via Latency-Aware Test-Time Scaling | May 26, 2025 | Math | —Unverified | 0 |
| AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models | May 25, 2025 | MathMathematical Reasoning | —Unverified | 0 |
| MMATH: A Multilingual Benchmark for Mathematical Reasoning | May 25, 2025 | MathMathematical Reasoning | CodeCode Available | 0 |
| Enumerate-Conjecture-Prove: Formally Solving Answer-Construction Problems in Math Competitions | May 24, 2025 | Automated Theorem ProvingMath | CodeCode Available | 0 |
| Steering LLM Reasoning Through Bias-Only Adaptation | May 24, 2025 | GSM8KMath | —Unverified | 0 |
| Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment? | May 24, 2025 | Code GenerationMath | —Unverified | 0 |