04:00
2026-08-12
arxiv.org
artificial-intelligence
When Chain-of-Thought Helps and When It Hurts: An Empirical Investigation of the Serial-Depth Bottleneck in LLM Reasoning
A new arXiv study (2608.09942v1) finds that chain-of-thought (CoT) prompting is not a universal enhancer of large language model reasoning, but rather a bandwidth bypass that helps only when serial co…