ScienceStack
Explore
Plans and pricing
FAQ
Contact us
Table of Contents
Fetching ...
Sign In
Toggle theme
Paper
Download
Prompt Repetition Improves Non-Reasoning LLMs
Published: December 17, 2025
arXiv: 2512.14982v1
View on Semantic Scholar
Cite
Authors
Yaniv Leviathan
,
Matan Kalman
,
Yossi Matias
Abstract
When not using reasoning, repeating the input prompt improves performance for popular models (Gemini, GPT, Claude, and Deepseek) without increasing the number of generated tokens or latency.
