| Thinkless: LLM Learns When to Think | May 19, 2025 | GSM8KMath | CodeCode Available | 3 |
| Synthetic Data RL: Task Definition Is All You Need | May 18, 2025 | AllGSM8K | CodeCode Available | 2 |
| SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization | May 18, 2025 | MathMathematical Reasoning | —Unverified | 0 |
| Efficient RL Training for Reasoning Models via Length-Aware Optimization | May 18, 2025 | Math | CodeCode Available | 1 |
| MARGE: Improving Math Reasoning for LLMs with Guided Exploration | May 18, 2025 | MathMathematical Reasoning | CodeCode Available | 0 |
| HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class | May 17, 2025 | MathMathematical Problem-Solving | CodeCode Available | 0 |
| LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades | May 17, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities | May 17, 2025 | Math | —Unverified | 0 |
| HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM Systems | May 17, 2025 | Arithmetic ReasoningCode Generation | CodeCode Available | 1 |
| Critique-Guided Distillation: Improving Supervised Fine-tuning via Better Distillation | May 16, 2025 | MathMMLU | —Unverified | 0 |
