Saad B. Alarifi, Mohammed A. Alam · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.30223 · cited by 0 works (OpenAlex) · open-access PDF
大型语言模型在竞争式编程中越来越多地使用,他们的输出对提示的表达方式敏感。先前的工作比较了对竞争式编程的准确度的提示策略,但不是运行速度,并且没有将结果置于人体性能的位置。在GPT-5.5上的九种风格中的一个提示的探索性研究中,至少在这些任务中的三个准确性任务中,从国际计算机科学奥林匹克赛(IOI)和两个NP硬速度任务中比较了提示策略,我们发现没有单个提示是最好的:最强的提示取决于任务类型,以及结果是否被平均或中间级研究概括了,这表明,至少对于这些任务,提示风格应该与目标相匹配,而不是被视为普遍性的。
Machine translation (Meta M2M100); the English original follows.
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. 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. 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. 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.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Task (project management), Metric (unit), Situated, Artificial intelligence, Style (visual arts)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30223, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange