Skeleton-of-Thought published
Skeleton-of-Thought published — first builds the skeleton of the answer, then decodes each point in parallel
Why it matters
A branch that applied reasoning prompting to latency optimization
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2307.15337Added in Week 35, 2026 · See that week