GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

[Free GPT-4]
[PDF] arxiv.org

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

H Xu, X Wu, W Wang, Z Li, D Zheng, B Chen… - arxiv preprint arxiv …, 2025 - arxiv.org
Can scaling transform reasoning? In this work, we explore the untapped potential of scaling
Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of …
Enregistrer Citer Autres articles Version HTML