arxiv:2512.14982

Prompt Repetition Improves Non-Reasoning LLMs

Published on Dec 17, 2025

Authors:

Abstract

Repeating the input prompt enhances performance for leading models (Gemini, GPT, Claude, Deepseek) without increasing token count or latency.

AI-generated summary

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.

View arXiv page View PDF Add to collection

Community

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

Get this paper in your agent:

hf papers read 2512.14982

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 4

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2512.14982 in a dataset README.md to link it from this page.

Prompt Repetition Improves Non-Reasoning LLMs

Abstract

Community

Models citing this paper 4

Datasets citing this paper 0

Spaces citing this paper 3

Collections including this paper 1