Newest papers

How Prompt Style Affects AI Accuracy and Speed in Competitive Programming

Saad B. Alarifi, Mohammed A. Alam · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30223 · cited by 0 works (OpenAlex) · open-access PDF

German

Große Sprachmodelle werden zunehmend in der wettbewerbsfähigen Programmierung eingesetzt, und ihre Ausgaben sind empfindlich auf die Art und Weise, wie ein Prompt ausgedrückt wird. Frühere Arbeiten haben Prompt-Strategien für Genauigkeit bei der wettbewerbsfähigen Programmierung verglichen, aber nicht für die Laufzeitgeschwindigkeit, und haben die Ergebnisse nicht gegen die menschliche Leistung gesetzt. In einer erforschenden Studie von einem Prompt in jedem der neun Stile auf GPT-5.5 über drei Genauigkeitsaufgaben aus der Internationalen Olympiade in der Informatik (IOI) und zwei NP-Hard-Geschwindigkeitsaufgaben, fanden wir, dass kein einzelner Prompt der beste war: der stärkste Prompt hängt von der Aufgabe

Machine translation (Meta M2M100); the English original follows.

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. 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)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange