How Many Thoughts Can a Vector Hold? The Capacity of Reasoning by Superposition
arXiv:2609.13747v1 Announce Type: new Abstract: Large language models solve hard problems through intermediate computations across multi-step reasoning. Traditional chain-of-thought encodes these computations as tokens. Recent continuous...
Read more: https://arxiv.org/abs/2609.13747
Scan with your phone
Scan with your phone