《LLM輔助重構與遊戲玩法特徵生成之探索性案例研究：以無盡跑酷遊戲為例》

摘要

大型語言模型（LLMs）日益被用於支援軟體開發，但在實際遊戲開發情境中的實用性仍探索不足，特別是當生成的程式碼必須整合至現有遊戲軟體系統時。本文針對自訂的 Python/Pygame 無盡跑酷遊戲，對 GPT-4o 進行一項探索性實證案例研究。該研究選取六項開發任務：三項局部重構任務與三項涉及遊戲玩法功能生成的任務。其實作結果透過軟體度量、單元測試及人工遊戲體驗評估進行評量。在此案例研究中，三項選取的重構任務在功能層面均成功完成，而三項遊戲玩法功能生成任務中僅有一項達成正確整合的功能。研究發現顯示，在此設定下，GPT-4o 處理局部轉換的可靠度優於需要跨多個現有系統進行新遊戲互動的任務。考量本研究的探索性單案例設計，這些結果最適合解讀為指標性觀察，而非類別層級模型表現的可推廣證據。總體而言，本文針對 LLM 輔助重構與遊戲玩法功能生成在現有遊戲軟體系統中的機會與限制，提供了一個透明且基於案例的記述。

English

Large language models (LLMs) are increasingly used to support software development, but their practical usefulness in applied game-development settings remains underexplored, especially when generated code must be integrated into an existing game software system. This paper presents an exploratory empirical case study of GPT-4o in a custom Python/Pygame endless runner. The study examines six selected development tasks: three localized refactoring tasks and three tasks involving gameplay feature generation. The resulting implementations were evaluated using software metrics, unit tests, and manual gameplay assessments. In this case study, all three selected refactoring tasks were completed successfully in functional terms, whereas only one of the three selected gameplay feature generation tasks resulted in a correctly integrated feature. The findings suggest that, in this setting, GPT-4o handled localized transformations more reliably than tasks requiring new gameplay interactions across multiple existing systems. Given the exploratory single-case design, these results are best interpreted as indicative observations rather than as generalizable evidence of category-level model performance. Overall, the paper contributes a transparent case-based account of the opportunities and limitations of LLM-assisted refactoring and gameplay feature generation in an existing game software system.