How Prompt Style Affects AI Accuracy and Speed in Competitive Programming

查看原文 / View Original 编辑 / Edit

Computer Science > Machine Learning arXiv:2610.30223 (cs) [Submitted on 21 Oct 2026] Title: How Prompt Style Affects AI Accuracy and Speed in Competitive Programming Authors: Saad B. Alarifi, Mohammed A. Alam.

计算机科学 > 机器学习 arXiv:2610.30223 (cs) [提交于 2026 年 10 月 21 日] 标题：提示词风格如何影响人工智能在竞技编程中的准确性和速度作者：Saad B. Alarifi, Mohammed A. Alam。

Abstract: Large language models are increasingly used in competitive programming, and their outputs are sensitive to how a prompt is phrased. Prior work has compared prompt strategies for accuracy on competitive programming, but not for runtime speed, and has not situated the results against human performance.

摘要：大型语言模型在竞技编程中的应用日益广泛，其输出结果对提示词的措辞非常敏感。以往的研究比较了竞技编程中提示词策略的准确性，但未涉及运行速度，也未将结果与人类表现进行对比。

In an exploratory study of one prompt in each of nine styles on GPT-5.5 across three accuracy tasks from the International Olympiad in Informatics (IOI) and two NP-hard speed tasks, we found that no single prompt was best: the strongest prompt depended on the task type and on whether results were summarized by the mean or the median, suggesting that, at least for these tasks, prompt style should be matched to the objective rather than treated as universal.

在一项探索性研究中，我们针对 GPT-5.5 模型，在来自国际信息学奥林匹克竞赛（IOI）的三项准确性任务和两项 NP-难速度任务中，对九种风格的提示词各进行了一次测试。我们发现没有哪种提示词是绝对最优的：最有效的提示词取决于任务类型以及结果是按平均值还是中位数进行汇总，这表明至少对于这些任务而言，提示词风格应根据目标进行匹配，而非作为通用方案。

Many differences in mean scores came from a few outlier runs, showing that evaluating prompting by a single metric can obscure how much its effectiveness varies. Compared descriptively with human IOI contestants, who worked under different conditions, the AI was neither strictly better nor strictly worse, exceeding the average contestant on one task but falling short on the other two.

平均分数的许多差异源于少数异常运行结果，这表明仅通过单一指标评估提示词可能会掩盖其有效性的波动程度。与在不同条件下工作的人类 IOI 参赛者进行描述性比较后发现，人工智能的表现既非绝对优于也非绝对劣于人类，它在一项任务中超过了平均水平，但在另外两项任务中表现不足。

By extending prompt comparison from accuracy to runtime speed and grounding it against human performance, this study gives a broader picture of how prompt style affects competitive programming performance.

通过将提示词比较从准确性扩展到运行速度，并将其与人类表现进行对比，本研究更全面地展示了提示词风格如何影响竞技编程的表现。