| SIFT: Grounding LLM Reasoning in Contexts via Stickers | Feb 19, 2025 | GSM8KMath | CodeCode Available | 2 |
| From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education | Feb 19, 2025 | DiagnosticGSM8K | —Unverified | 0 |
| TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation | Feb 19, 2025 | Dataset GenerationGSM8K | CodeCode Available | 0 |
| Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models | Feb 18, 2025 | Data AugmentationGSM8K | —Unverified | 0 |
| MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task | Feb 17, 2025 | Code CompletionGSM8K | —Unverified | 0 |
| TokenSkip: Controllable Chain-of-Thought Compression in LLMs | Feb 17, 2025 | GSM8K | CodeCode Available | 3 |
| SMART: Self-Aware Agent for Tool Overuse Mitigation | Feb 17, 2025 | GSM8KLarge Language Model | CodeCode Available | 1 |
| Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls | Feb 16, 2025 | Computational EfficiencyGSM8K | CodeCode Available | 0 |
| Uncertainty-Aware Search and Value Models: Mitigating Search Scaling Flaws in LLMs | Feb 16, 2025 | GSM8KThompson Sampling | —Unverified | 0 |
| Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning | Feb 16, 2025 | GSM8K | —Unverified | 0 |
