Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought

Published in ArXiv, 2025

Recommended citation: Zeyu Gan, Hao Yi, Yong Liu. Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought. arXiv preprint arXiv:2509.04027, 2025. https://arxiv.org/abs/2509.04027